A Genomics-Driven Artificial Intelligence-Based Model Classifies Breast Invasive Lobular Carcinoma and Discovers CDH1 Inactivating Mechanisms.

Artificial intelligence (AI) systems can improve cancer diagnosis, yet their development often relies on subjective histologic features as ground truth for training. Herein, we developed an AI model applied to histologic whole-slide images using CDH1 biallelic mutations, pathognomonic for invasive lobular carcinoma (ILC) in breast neoplasms, as ground truth. The model accurately predicted CDH1 biallelic mutations (accuracy = 0.95) and diagnosed ILC (accuracy = 0.96). A total of 74% of samples classified by the AI model as having CDH1 biallelic mutations but lacking these alterations displayed alternative CDH1 inactivating mechanisms, including a deleterious CDH1 fusion gene and noncoding CDH1 genetic alterations. Analysis of internal and external validation cohorts demonstrated 0.95 and 0.89 accuracy for ILC diagnosis, respectively. The latent features of the AI model correlated with human-explainable histopathologic features. Taken together, this study reports the construction of an AI algorithm trained using a genetic rather than histologic ground truth that can robustly classify ILCs and uncover CDH1 inactivating mechanisms, providing the basis for orthogonal ground truth utilization for development of diagnostic AI models applied to whole-slide image. Significance: Genetic alterations linked to strong genotypic-phenotypic correlations can be utilized to develop AI systems applied to pathology that facilitate cancer diagnosis and biologic discoveries.

A foundation model for clinical-grade computational pathology and rare cancers detection.

The analysis of histopathology images with artificial intelligence aims to enable clinical decision support systems and precision medicine. The success of such applications depends on the ability to model the diverse patterns observed in pathology images. To this end, we present Virchow, the largest foundation model for computational pathology to date. In addition to the evaluation of biomarker prediction and cell identification, we demonstrate that a large foundation model enables pan-cancer detection, achieving 0.95 specimen-level area under the (receiver operating characteristic) curve across nine common and seven rare cancers. Furthermore, we show that with less training data, the pan-cancer detector built on Virchow can achieve similar performance to tissue-specific clinical-grade models in production and outperform them on some rare variants of cancer. Virchow's performance gains highlight the value of a foundation model and open possibilities for many high-impact applications with limited amounts of labeled training data.

Artificial Intelligence Helps Pathologists Increase Diagnostic Accuracy and Efficiency in the Detection of Breast Cancer Lymph Node Metastases.

The detection of lymph node metastases is essential for breast cancer staging, although it is a tedious and time-consuming task where the sensitivity of pathologists is suboptimal. Artificial intelligence (AI) can help pathologists detect lymph node metastases, which could help alleviate workload issues. We studied how pathologists' performance varied when aided by AI. An AI algorithm was trained using more than 32 000 breast sentinel lymph node whole slide images (WSIs) matched with their corresponding pathology reports from more than 8000 patients. The algorithm highlighted areas suspicious of harboring metastasis. Three pathologists were asked to review a dataset comprising 167 breast sentinel lymph node WSIs, of which 69 harbored cancer metastases of different sizes, enriched for challenging cases. Ninety-eight slides were benign. The pathologists read the dataset twice, both digitally, with and without AI assistance, randomized for slide and reading orders to reduce bias, separated by a 3-week washout period. Their slide-level diagnosis was recorded, and they were timed during their reads. The average reading time per slide was 129 seconds during the unassisted phase versus 58 seconds during the AI-assisted phase, resulting in an overall efficiency gain of 55% ( P <0.001). These efficiency gains are applied to both benign and malignant WSIs. Two of the 3 reading pathologists experienced significant sensitivity improvements, from 74.5% to 93.5% ( P ≤0.006). This study highlights that AI can help pathologists shorten their reading times by more than half and also improve their metastasis detection rate.

Femoroacetabular Variations Are Predisposing Factors for Traumatic Posterior Hip Dislocation.

BACKGROUND: Although high-energy trauma mechanisms are generally considered to cause traumatic posterior hip dislocations, femoroacetabular variations are assumed to contribute to low-impact hip dislocations. Thus, the present study aimed to identify morphologic femoral and acetabular risk factors that may also contribute to posterior hip dislocations in high-energy trauma mechanisms. METHODS: The acetabular and femoral morphology of 83 hips with a traumatic posterior dislocation following a high-energy trauma mechanism were analyzed and matched to a control group of 83 patients who sustained high-energy trauma without a hip injury. The lateral center-edge angle, acetabular index, acetabular depth/width ratio, cranial and central acetabular version angles, and the anterior and posterior acetabular sector angles were measured on computed tomography to quantify femoroacetabular impingement (FAI) morphology, acetabular version, and coverage. The caput-collum-diaphyseal angle and the alpha angles in the coronal and axial planes were measured to detect cam-type FAI deformity. A receiver operating characteristic curve was utilized to determine threshold values for an increased risk of hip dislocation. RESULTS: Acetabular retroversion and posterior acetabular undercoverage were significantly increased in patients with hip dislocations compared with controls (p < 0.001). The central acetabular version angle and posterior acetabular sector angle that indicated an increased risk of hip dislocation were ≤9° and ≤90°, respectively. Cam-type FAI deformity and coxa valga were significantly increased in the dislocation group (p < 0.001). The anterolateral alpha angle that indicated an increased dislocation risk was ≥47°. CONCLUSIONS: Acetabular retroversion, posterior acetabular undercoverage, and cam-type FAI morphology may be risk factors contributing to traumatic posterior hip dislocation in high-energy trauma mechanisms. LEVEL OF EVIDENCE: Prognostic Level III . See Instructions for Authors for a complete description of levels of evidence.

Intermediate to Long-Term Results Following Traumatic Hip Dislocation: Characteristics, CT-Based Analysis, and Patient-Reported Outcome Measures.

BACKGROUND: Traumatic hip dislocation is a rare yet severe injury. As the long-term morbidity, subsequent complications, and clinical outcomes are nearly unknown, we aimed to analyze traumatic hip dislocations and identify specific factors that may predict the clinical outcome. METHODS: Data on injury-related characteristics and computed tomographic (CT) scans for all consecutive adult patients who had been managed for traumatic hip dislocation between 2009 and 2021 were analyzed. At the time of follow-up, the patients were assessed with regard to osteonecrosis, posttraumatic osteoarthritis (OA), further operations and complications, return to sports and work, and patient-reported outcome measures (PROMs), including the Tegner Activity Scale and modified Harris hip score. RESULTS: One hundred and twelve patients (mean age [and standard deviation], 43.12 ± 16.6 years) were included. Associated acetabular rim and femoral head fractures (Pipkin Type I to IV) were observed in 44% and 40% of patients, respectively. Concomitant injuries occurred in 67% of the patients, most commonly involving the knee (29% of patients). Sixty-nine patients (61.6%) were available for follow-up; the mean duration of follow-up was 6.02 ± 3.76 years. The rates of osteonecrosis and posttraumatic OA were 13% and 31.9%, respectively, and were independent of the timing of hip reduction, leading to subsequent total hip arthroplasty (THA) in 19% of patients. Sciatic nerve injury occurred in 27.5% of the patients who were available for follow-up. Both THA and sciatic nerve injury were associated with posterior acetabular rim or Pipkin Type-IV fractures (p < 0.001). Only 33.3% of the patients returned to their pre-injury level of sports, 24.6% did not return to work, and 27.5% reported having sexual dysfunction. PROMs (Tegner Activity Scale, modified Harris hip score) were significantly worse in patients with osteonecrosis, posttraumatic OA, or residual sciatic nerve injury (p < 0.05). CONCLUSIONS: Traumatic hip dislocations are predominantly associated with Pipkin and acetabular rim fractures, leading to overall limitations of activities of daily living, sports, and sexual function at intermediate to long-term follow-up. Patients with associated acetabular rim or Pipkin Type-IV fractures are most likely to require THA for the treatment of osteonecrosis or posttraumatic OA and are at greater risk for sustaining sciatic nerve injury. LEVEL OF EVIDENCE: Prognostic Level IV . See Instructions for Authors for a complete description of levels of evidence.

Deep learning for [18F]fluorodeoxyglucose-PET-CT classification in patients with lymphoma: a dual-centre retrospective analysis.

BACKGROUND: The rising global cancer burden has led to an increasing demand for imaging tests such as [18F]fluorodeoxyglucose ([18F]FDG)-PET-CT. To aid imaging specialists in dealing with high scan volumes, we aimed to train a deep learning artificial intelligence algorithm to classify [18F]FDG-PET-CT scans of patients with lymphoma with or without hypermetabolic tumour sites. METHODS: In this retrospective analysis we collected 16 583 [18F]FDG-PET-CTs of 5072 patients with lymphoma who had undergone PET-CT before or after treatment at the Memorial Sloa Kettering Cancer Center, New York, NY, USA. Using maximum intensity projection (MIP), three dimensional (3D) PET, and 3D CT data, our ResNet34-based deep learning model (Lymphoma Artificial Reader System [LARS]) for [18F]FDG-PET-CT binary classification (Deauville 1-3 vs 4-5), was trained on 80% of the dataset, and tested on 20% of this dataset. For external testing, 1000 [18F]FDG-PET-CTs were obtained from a second centre (Medical University of Vienna, Vienna, Austria). Seven model variants were evaluated, including MIP-based LARS-avg (optimised for accuracy) and LARS-max (optimised for sensitivity), and 3D PET-CT-based LARS-ptct. Following expert curation, areas under the curve (AUCs), accuracies, sensitivities, and specificities were calculated. FINDINGS: In the internal test cohort (3325 PET-CTs, 1012 patients), LARS-avg achieved an AUC of 0·949 (95% CI 0·942-0·956), accuracy of 0·890 (0·879-0·901), sensitivity of 0·868 (0·851-0·885), and specificity of 0·913 (0·899-0·925); LARS-max achieved an AUC of 0·949 (0·942-0·956), accuracy of 0·868 (0·858-0·879), sensitivity of 0·909 (0·896-0·924), and specificity of 0·826 (0·808-0·843); and LARS-ptct achieved an AUC of 0·939 (0·930-0·948), accuracy of 0·875 (0·864-0·887), sensitivity of 0·836 (0·817-0·855), and specificity of 0·915 (0·901-0·927). In the external test cohort (1000 PET-CTs, 503 patients), LARS-avg achieved an AUC of 0·953 (0·938-0·966), accuracy of 0·907 (0·888-0·925), sensitivity of 0·874 (0·843-0·904), and specificity of 0·949 (0·921-0·960); LARS-max achieved an AUC of 0·952 (0·937-0·965), accuracy of 0·898 (0·878-0·916), sensitivity of 0·899 (0·871-0·926), and specificity of 0·897 (0·871-0·922); and LARS-ptct achieved an AUC of 0·932 (0·915-0·948), accuracy of 0·870 (0·850-0·891), sensitivity of 0·827 (0·793-0·863), and specificity of 0·913 (0·889-0·937). INTERPRETATION: Deep learning accurately distinguishes between [18F]FDG-PET-CT scans of lymphoma patients with and without hypermetabolic tumour sites. Deep learning might therefore be potentially useful to rule out the presence of metabolically active disease in such patients, or serve as a second reader or decision support tool. FUNDING: National Institutes of Health-National Cancer Institute Cancer Center Support Grant.

Diagnosis and treatment of Hymenoptera venom allergy: S2k Guideline of the German Society of Allergology and Clinical Immunology (DGAKI) in collaboration with the Arbeitsgemeinschaft für Berufs- und Umweltdermatologie e.V. (ABD), the Medical Association of German Allergologists (AeDA), the German Society of Dermatology (DDG), the German Society of Oto-Rhino-Laryngology, Head and Neck Surgery (DGHNOKC), the German Society of Pediatrics and Adolescent Medicine (DGKJ), the Society for Pediatric Allergy and Environmental Medicine (GPA), German Respiratory Society (DGP), and the Austrian Society for Allergy and Immunology (ÖGAI).

Hymenoptera venom (HV) is injected into the skin during a sting by Hymenoptera such as bees or wasps. Some components of HV are potential allergens and can cause large local and/or systemic allergic reactions (SAR) in sensitized individuals. During their lifetime, ~ 3% of the general population will develop SAR following a Hymenoptera sting. This guideline presents the diagnostic and therapeutic approach to SAR following Hymenoptera stings. Symptomatic therapy is usually required after a severe local reaction, but specific diagnosis or allergen immunotherapy (AIT) with HV (VIT) is not necessary. When taking a patient's medical history after SAR, clinicians should discuss possible risk factors for more frequent stings and more severe anaphylactic reactions. The most important risk factors for more severe SAR are mast cell disease and, especially in children, uncontrolled asthma. Therefore, if the SAR extends beyond the skin (according to the Ring and Messmer classification: grade > I), the baseline serum tryptase concentration shall be measured and the skin shall be examined for possible mastocytosis. The medical history should also include questions specific to asthma symptoms. To demonstrate sensitization to HV, allergists shall determine concentrations of specific IgE antibodies (sIgE) to bee and/or vespid venoms, their constituents and other venoms as appropriate. If the results are negative less than 2 weeks after the sting, the tests shall be repeated (at least 4 - 6 weeks after the sting). If only sIgE to the total venom extracts have been determined, if there is double sensitization, or if the results are implausible, allergists shall determine sIgE to the different venom components. Skin testing may be omitted if in-vitro methods have provided a definitive diagnosis. If neither laboratory diagnosis nor skin testing has led to conclusive results, additional cellular testing can be performed. Therapy for HV allergy includes prophylaxis of reexposure, patient self treatment measures (including use of rescue medication) in the event of re-stings, and VIT. Following a grade I SAR and in the absence of other risk factors for repeated sting exposure or more severe anaphylaxis, it is not necessary to prescribe an adrenaline auto-injector (AAI) or to administer VIT. Under certain conditions, VIT can be administered even in the presence of previous grade I anaphylaxis, e.g., if there are additional risk factors or if quality of life would be reduced without VIT. Physicians should be aware of the contraindications to VIT, although they can be overridden in justified individual cases after weighing benefits and risks. The use of ß-blockers and ACE inhibitors is not a contraindication to VIT. Patients should be informed about possible interactions. For VIT, the venom extract shall be used that, according to the patient's history and the results of the allergy diagnostics, was the trigger of the disease. If, in the case of double sensitization and an unclear history regarding the trigger, it is not possible to determine the culprit venom even with additional diagnostic procedures, VIT shall be performed with both venom extracts. The standard maintenance dose of VIT is 100 µg HV. In adult patients with bee venom allergy and an increased risk of sting exposure or particularly severe anaphylaxis, a maintenance dose of 200 µg can be considered from the start of VIT. Administration of a non-sedating H1-blocking antihistamine can be considered to reduce side effects. The maintenance dose should be given at 4-weekly intervals during the first year and, following the manufacturer's instructions, every 5 - 6 weeks from the second year, depending on the preparation used; if a depot preparation is used, the interval can be extended to 8 weeks from the third year onwards. If significant recurrent systemic reactions occur during VIT, clinicians shall identify and as possible eliminate co-factors that promote these reactions. If this is not possible or if there are no such co-factors, if prophylactic administration of an H1-blocking antihistamine is not effective, and if a higher dose of VIT has not led to tolerability of VIT, physicians should should consider additional treatment with an anti IgE antibody such as omalizumab as off lable use. For practical reasons, only a small number of patients are able to undergo sting challenge tests to check the success of the therapy, which requires in-hospital monitoring and emergency standby. To perform such a provocation test, patients must have tolerated VIT at the planned maintenance dose. In the event of treatment failure while on treatment with an ACE inhibitor, physicians should consider discontinuing the ACE inhibitor. In the absence of tolerance induction, physicians shall increase the maintenance dose (200 µg to a maximum of 400 µg in adults, maximum of 200 µg HV in children). If increasing the maintenance dose does not provide adequate protection and there are risk factors for a severe anaphylactic reaction, physicians should consider a co-medication based on an anti-IgE antibody (omalizumab; off-label use) during the insect flight season. In patients without specific risk factors, VIT can be discontinued after 3 - 5 years if maintenance therapy has been tolerated without recurrent anaphylactic events. Prolonged or permanent VIT can be considered in patients with mastocytosis, a history of cardiovascular or respiratory arrest due to Hymenoptera sting (severity grade IV), or other specific constellations associated with an increased individual risk of recurrent and/or severe SAR (e.g., hereditary α-tryptasemia). In cases of strongly increased, unavoidable insect exposure, adults may receive VIT until the end of intense contact. The prescription of an AAI can be omitted in patients with a history of SAR grade I and II when the maintenance dose of VIT has been reached and tolerated, provided that there are no additional risk factors. The same holds true once the VIT has been terminated after the regular treatment period. Patients with a history of SAR grade ≥ III reaction, or grade II reaction combined with additional factors that increase the risk of non response or repeated severe sting reactions, should carry an emergency kit, including an AAI, during VIT and after regular termination of the VIT.

Guideline for allergological diagnosis of drug hypersensitivity reactions: S2k Guideline of the German Society for Allergology and Clinical Immunology (DGAKI) in cooperation with the German Dermatological Society (DDG), the Association of German Allergologists (ÄDA), the German Society for Pediatric Allergology (GPA), the German Contact Dermatitis Research Group (DKG), the German Society for Pneumology (DGP), the German Society of Otorhinolaryngology, Head and Neck Surgery, the Austrian Society of Allergology and Immunology (ÖGAI), the Austrian Society of Dermatology and Venereology (ÖGDV), the German Academy of Allergology and Environmental Medicine (DAAU), and the German Documentation Center for Severe Skin Reactions (dZh).

Not available.

[Acute soft Tissue Infection with impending Loss of Finger in amniotic Band Syndrome of a 22-years-old Patient with palmoplantar Keratoderma congenital Alopecia Syndrome Type II]. / Akute Weichteilinfektion mit drohendem Fingerverlust bei Schnürfurchensyndrom einer 22-jährigen Patientin mit palmoplantarem Keratoderm-kongenitalem Alopezie-Syndrom Typ II.

We report on the treatment of a 22-year-old female patient with an acute soft tissue infection in the area of an amniotic band due to palmoplantar keratoderma congenital alopecia syndrome (PPKCA) type II, a very rare genodermatosis with less than 20 cases described in literature. An acute soft tissue infection distal from the pre-existing constriction ring with hyperkeratosis on the right small finger led to a decompensation of the venous and lymphatic drain with imminent loss of the finger. Due to urgent surgical treatment with decompression and debridement of the dorsal soft tissue infection, microsurgical circular resection of the constriction ring and primary wound closure the finger could be preserved. After soft tissue consolidation and hand therapy, the patient achieved free movement of the small finger with subjective freedom of symptoms and good aesthetic results.

Seizures as a Struggle between Life and Death: An Existential Approach to the Psychosocial Impact of Seizures in Candidates for Epilepsy Surgery.

INTRODUCTION: Mental health comorbidities such as depression and anxiety are common in epilepsy, especially among people with pharmacoresistant epilepsy who are candidates for epilepsy surgery. The Psychology Task Force of the International League Against Epilepsy advised that psychological interventions should be integrated into comprehensive epilepsy care. METHODS: To better understand the psychological impact of epilepsy and epileptic seizures in epilepsy surgery candidates, we analysed interviews with this subgroup of patients using Karl Jaspers' concept of limit situations, which are characterised by a confrontation with the limits and challenges of life. These are especially chance, randomness, and unpredictability, death and finitude of life, struggle and self-assertion, guilt, failure, and falling short of one's aspirations. RESULTS: In 43 interviews conducted with 15 people with drug-resistant epilepsy who were candidates for epilepsy surgery, we found that these themes are recurrent and have a large psychosocial impact, which can result in depression and anxiety. For some people, epileptic seizures appear to meet the criteria for traumatic events. CONCLUSION: Understanding epilepsy and seizures as existential challenges complements the neurobiological explanations for psychological comorbidities and can help tailor psychological interventions to the specific needs of people with epilepsy, especially those who are candidates for surgical treatment.

Telestration with augmented reality improves surgical performance through gaze guidance.

BACKGROUND: In minimally invasive surgery (MIS), trainees need to learn how to interpret the operative field displayed on the laparoscopic screen. Experts currently guide trainees mainly verbally during laparoscopic procedures. A newly developed telestration system with augmented reality (iSurgeon) allows the instructor to display hand gestures in real-time on the laparoscopic screen in augmented reality to provide visual expert guidance (telestration). This study analysed the effect of telestration guided instructions on gaze behaviour during MIS training. METHODS: In a randomized-controlled crossover study, 40 MIS naive medical students performed 8 laparoscopic tasks with telestration or with verbal instructions only. Pupil Core eye-tracking glasses were used to capture the instructor's and trainees' gazes. Gaze behaviour measures for tasks 1-7 were gaze latency, gaze convergence and collaborative gaze convergence. Performance measures included the number of errors in tasks 1-7 and trainee's ratings in structured and standardized performance scores in task 8 (ex vivo porcine laparoscopic cholecystectomy). RESULTS: There was a significant improvement 1-7 on gaze latency [F(1,39) = 762.5, p < 0.01, ηp2 = 0.95], gaze convergence [F(1,39) = 482.8, p < 0.01, ηp2 = 0.93] and collaborative gaze convergence [F(1,39) = 408.4, p < 0.01, ηp2 = 0.91] upon instruction with iSurgeon. The number of errors was significantly lower in tasks 1-7 (0.18 ± 0.56 vs. 1.94 ± 1.80, p < 0.01) and the score ratings for laparoscopic cholecystectomy were significantly higher with telestration (global OSATS: 29 ± 2.5 vs. 25 ± 5.5, p < 0.01; task-specific OSATS: 60 ± 3 vs. 50 ± 6, p < 0.01). CONCLUSIONS: Telestration with augmented reality successfully improved surgical performance. The trainee's gaze behaviour was improved by reducing the time from instruction to fixation on targets and leading to a higher convergence of the instructor's and the trainee's gazes. Also, the convergence of trainee's gaze and target areas increased with telestration. This confirms augmented reality-based telestration works by means of gaze guidance in MIS and could be used to improve training outcomes.

Deep Interactive Learning-based ovarian cancer segmentation of H&E-stained whole slide images to study morphological patterns of BRCA mutation.

Deep learning has been widely used to analyze digitized hematoxylin and eosin (H&E)-stained histopathology whole slide images. Automated cancer segmentation using deep learning can be used to diagnose malignancy and to find novel morphological patterns to predict molecular subtypes. To train pixel-wise cancer segmentation models, manual annotation from pathologists is generally a bottleneck due to its time-consuming nature. In this paper, we propose Deep Interactive Learning with a pretrained segmentation model from a different cancer type to reduce manual annotation time. Instead of annotating all pixels from cancer and non-cancer regions on giga-pixel whole slide images, an iterative process of annotating mislabeled regions from a segmentation model and training/finetuning the model with the additional annotation can reduce the time. Especially, employing a pretrained segmentation model can further reduce the time than starting annotation from scratch. We trained an accurate ovarian cancer segmentation model with a pretrained breast segmentation model by 3.5 hours of manual annotation which achieved intersection-over-union of 0.74, recall of 0.86, and precision of 0.84. With automatically extracted high-grade serous ovarian cancer patches, we attempted to train an additional classification deep learning model to predict BRCA mutation. The segmentation model and code have been released at https://github.com/MSKCC-Computational-Pathology/DMMN-ovary.

Deep Learning-Based Objective and Reproducible Osteosarcoma Chemotherapy Response Assessment and Outcome Prediction.

Osteosarcoma is the most common primary bone cancer, whose standard treatment includes pre-operative chemotherapy followed by resection. Chemotherapy response is used for prognosis and management of patients. Necrosis is routinely assessed after chemotherapy from histology slides on resection specimens, where necrosis ratio is defined as the ratio of necrotic tumor/overall tumor. Patients with necrosis ratio ≥90% are known to have a better outcome. Manual microscopic review of necrosis ratio from multiple glass slides is semiquantitative and can have intraobserver and interobserver variability. In this study, an objective and reproducible deep learning-based approach was proposed to estimate necrosis ratio with outcome prediction from scanned hematoxylin and eosin whole slide images (WSIs). To conduct the study, 103 osteosarcoma cases with 3134 WSIs were collected. Deep Multi-Magnification Network was trained to segment multiple tissue subtypes, including viable tumor and necrotic tumor at a pixel level and to calculate case-level necrosis ratio from multiple WSIs. Necrosis ratio estimated by the segmentation model highly correlates with necrosis ratio from pathology reports manually assessed by experts. Furthermore, patients were successfully stratified to predict overall survival with P = 2.4 × 10-6 and progression-free survival with P = 0.016. This study indicates that deep learning can support pathologists as an objective tool to analyze osteosarcoma from histology for assessing treatment response and predicting patient outcome.

Clinical Validation of Artificial Intelligence-Augmented Pathology Diagnosis Demonstrates Significant Gains in Diagnostic Accuracy in Prostate Cancer Detection.

CONTEXT.­: Prostate cancer diagnosis rests on accurate assessment of tissue by a pathologist. The application of artificial intelligence (AI) to digitized whole slide images (WSIs) can aid pathologists in cancer diagnosis, but robust, diverse evidence in a simulated clinical setting is lacking. OBJECTIVE.­: To compare the diagnostic accuracy of pathologists reading WSIs of prostatic biopsy specimens with and without AI assistance. DESIGN.­: Eighteen pathologists, 2 of whom were genitourinary subspecialists, evaluated 610 prostate needle core biopsy WSIs prepared at 218 institutions, with the option for deferral. Two evaluations were performed sequentially for each WSI: initially without assistance, and immediately thereafter aided by Paige Prostate (PaPr), a deep learning-based system that provides a WSI-level binary classification of suspicious for cancer or benign and pinpoints the location that has the greatest probability of harboring cancer on suspicious WSIs. Pathologists' changes in sensitivity and specificity between the assisted and unassisted modalities were assessed, together with the impact of PaPr output on the assisted reads. RESULTS.­: Using PaPr, pathologists improved their sensitivity and specificity across all histologic grades and tumor sizes. Accuracy gains on both benign and cancerous WSIs could be attributed to PaPr, which correctly classified 100% of the WSIs showing corrected diagnoses in the PaPr-assisted phase. CONCLUSIONS.­: This study demonstrates the effectiveness and safety of an AI tool for pathologists in simulated diagnostic practice, bridging the gap between computational pathology research and its clinical application, and resulted in the first US Food and Drug Administration authorization of an AI system in pathology.

Addition of shock wave therapy to nail dynamization increases the chance of long-bone non-union healing.

BACKGROUND: Long-bone non-unions after intramedullary nailing can be treated by nail dynamization or focused high-energy extracorporal shock wave therapy (fESWT). The objective of this study was to assess the effect of the combination therapy of nail dynamization and fESWT on long-bone non-unions. MATERIALS AND METHODS: 49 patients with long-bone non-unions (femur and tibia) after nailing were treated with nail dynamization (group D, n = 15), fESWT (group S, n = 17) or nail dynamization in addition to fESWT (group DS, n = 17). Patients were followed up for 6 months retrospectively. Furthermore, age, sex, Non-Union Scoring System (NUSS) score, time intervals from primary and last surgery until intervention and smoking status were analysed for their correlations to bone union. RESULTS: Union rates were 60% for group D, 64.7% for group S and 88.2% for group DS, with a significant difference between group D and DS (p = 0.024). Successful treatment was correlated with high age (OR 1.131; 95% CI 1.009-1.268; p = 0.034), female gender (OR 0.009; 95% CI 0.000-0.89; p = 0.039), low NUSS score (OR 0.839; 95% CI 0.717-0.081; p = 0.028) and negative smoking status (OR 86.018; 95% CI 3.051-2425.038; p = 0.009). CONCLUSIONS: Data from the present study indicate that the combination therapy of nail dynamization and fESWT leads to a higher union rate than dynamization or fESWT alone. LEVEL OF EVIDENCE: Level 3.

Deep Learning for Basal Cell Carcinoma Detection for Reflectance Confocal Microscopy.

Basal cell carcinoma (BCC) is the most common skin cancer, with over 2 million cases diagnosed annually in the United States. Conventionally, BCC is diagnosed by naked eye examination and dermoscopy. Suspicious lesions are either removed or biopsied for histopathological confirmation, thus lowering the specificity of noninvasive BCC diagnosis. Recently, reflectance confocal microscopy, a noninvasive diagnostic technique that can image skin lesions at cellular level resolution, has shown to improve specificity in BCC diagnosis and reduced the number needed to biopsy by 2-3 times. In this study, we developed and evaluated a deep learning-based artificial intelligence model to automatically detect BCC in reflectance confocal microscopy images. The proposed model achieved an area under the curve for the receiver operator characteristic curve of 89.7% (stack level) and 88.3% (lesion level), a performance on par with that of reflectance confocal microscopy experts. Furthermore, the model achieved an area under the curve of 86.1% on a held-out test set from international collaborators, demonstrating the reproducibility and generalizability of the proposed automated diagnostic approach. These results provide a clear indication that the clinical deployment of decision support systems for the detection of BCC in reflectance confocal microscopy images has the potential for optimizing the evaluation and diagnosis of patients with skin cancer.

Integrated digital pathology at scale: A solution for clinical diagnostics and cancer research at a large academic medical center.

OBJECTIVE: Broad adoption of digital pathology (DP) is still lacking, and examples for DP connecting diagnostic, research, and educational use cases are missing. We blueprint a holistic DP solution at a large academic medical center ubiquitously integrated into clinical workflows; researchapplications including molecular, genetic, and tissue databases; and educational processes. MATERIALS AND METHODS: We built a vendor-agnostic, integrated viewer for reviewing, annotating, sharing, and quality assurance of digital slides in a clinical or research context. It is the first homegrown viewer cleared by New York State provisional approval in 2020 for primary diagnosis and remote sign-out during the COVID-19 (coronavirus disease 2019) pandemic. We further introduce an interconnected Honest Broker for BioInformatics Technology (HoBBIT) to systematically compile and share large-scale DP research datasets including anonymized images, redacted pathology reports, and clinical data of patients with consent. RESULTS: The solution has been operationally used over 3 years by 926 pathologists and researchers evaluating 288 903 digital slides. A total of 51% of these were reviewed within 1 month after scanning. Seamless integration of the viewer into 4 hospital systems clearly increases the adoption of DP. HoBBIT directly impacts the translation of knowledge in pathology into effective new health measures, including artificial intelligence-driven detection models for prostate cancer, basal cell carcinoma, and breast cancer metastases, developed and validated on thousands of cases. CONCLUSIONS: We highlight major challenges and lessons learned when going digital to provide orientation for other pathologists. Building interconnected solutions will not only increase adoption of DP, but also facilitate next-generation computational pathology at scale for enhanced cancer research.

Overcoming an Annotation Hurdle: Digitizing Pen Annotations from Whole Slide Images.

BACKGROUND: The development of artificial intelligence (AI) in pathology frequently relies on digitally annotated whole slide images (WSI). The creation of these annotations - manually drawn by pathologists in digital slide viewers - is time consuming and expensive. At the same time, pathologists routinely annotate glass slides with a pen to outline cancerous regions, for example, for molecular assessment of the tissue. These pen annotations are currently considered artifacts and excluded from computational modeling. METHODS: We propose a novel method to segment and fill hand-drawn pen annotations and convert them into a digital format to make them accessible for computational models. Our method is implemented in Python as an open source, publicly available software tool. RESULTS: Our method is able to extract pen annotations from WSI and save them as annotation masks. On a data set of 319 WSI with pen markers, we validate our algorithm segmenting the annotations with an overall Dice metric of 0.942, Precision of 0.955, and Recall of 0.943. Processing all images takes 15 min in contrast to 5 h manual digital annotation time. Further, the approach is robust against text annotations. CONCLUSIONS: We envision that our method can take advantage of already pen-annotated slides in scenarios in which the annotations would be helpful for training computational models. We conclude that, considering the large archives of many pathology departments that are currently being digitized, our method will help to collect large numbers of training samples from those data.

Multi-magnification-based machine learning as an ancillary tool for the pathologic assessment of shaved margins for breast carcinoma lumpectomy specimens.

The surgical margin status of breast lumpectomy specimens for invasive carcinoma and ductal carcinoma in situ (DCIS) guides clinical decisions, as positive margins are associated with higher rates of local recurrence. The "cavity shave" method of margin assessment has the benefits of allowing the surgeon to orient shaved margins intraoperatively and the pathologist to assess one inked margin per specimen. We studied whether a deep convolutional neural network, a deep multi-magnification network (DMMN), could accurately segment carcinoma from benign tissue in whole slide images (WSIs) of shave margin slides, and therefore serve as a potential screening tool to improve the efficiency of microscopic evaluation of these specimens. Applying the pretrained DMMN model, or the initial model, to a validation set of 408 WSIs (348 benign, 60 with carcinoma) achieved an area under the curve (AUC) of 0.941. After additional manual annotations and fine-tuning of the model, the updated model achieved an AUC of 0.968 with sensitivity set at 100% and corresponding specificity of 78%. We applied the initial model and updated model to a testing set of 427 WSIs (374 benign, 53 with carcinoma) which showed AUC values of 0.900 and 0.927, respectively. Using the pixel classification threshold selected from the validation set, the model achieved a sensitivity of 92% and specificity of 78%. The four false-negative classifications resulted from two small foci of DCIS (1 mm, 0.5 mm) and two foci of well-differentiated invasive carcinoma (3 mm, 1.5 mm). This proof-of-principle study demonstrates that a DMMN machine learning model can segment invasive carcinoma and DCIS in surgical margin specimens with high accuracy and has the potential to be used as a screening tool for pathologic assessment of these specimens.

Independent real-world application of a clinical-grade automated prostate cancer detection system.

Artificial intelligence (AI)-based systems applied to histopathology whole-slide images have the potential to improve patient care through mitigation of challenges posed by diagnostic variability, histopathology caseload, and shortage of pathologists. We sought to define the performance of an AI-based automated prostate cancer detection system, Paige Prostate, when applied to independent real-world data. The algorithm was employed to classify slides into two categories: benign (no further review needed) or suspicious (additional histologic and/or immunohistochemical analysis required). We assessed the sensitivity, specificity, positive predictive values (PPVs), and negative predictive values (NPVs) of a local pathologist, two central pathologists, and Paige Prostate in the diagnosis of 600 transrectal ultrasound-guided prostate needle core biopsy regions ('part-specimens') from 100 consecutive patients, and to ascertain the impact of Paige Prostate on diagnostic accuracy and efficiency. Paige Prostate displayed high sensitivity (0.99; CI 0.96-1.0), NPV (1.0; CI 0.98-1.0), and specificity (0.93; CI 0.90-0.96) at the part-specimen level. At the patient level, Paige Prostate displayed optimal sensitivity (1.0; CI 0.93-1.0) and NPV (1.0; CI 0.91-1.0) at a specificity of 0.78 (CI 0.64-0.89). The 27 part-specimens considered by Paige Prostate as suspicious, whose final diagnosis was benign, were found to comprise atrophy (n = 14), atrophy and apical prostate tissue (n = 1), apical/benign prostate tissue (n = 9), adenosis (n = 2), and post-atrophic hyperplasia (n = 1). Paige Prostate resulted in the identification of four additional patients whose diagnoses were upgraded from benign/suspicious to malignant. Additionally, this AI-based test provided an estimated 65.5% reduction of the diagnostic time for the material analyzed. Given its optimal sensitivity and NPV, Paige Prostate has the potential to be employed for the automated identification of patients whose histologic slides could forgo full histopathologic review. In addition to providing incremental improvements in diagnostic accuracy and efficiency, this AI-based system identified patients whose prostate cancers were not initially diagnosed by three experienced histopathologists. © 2021 The Authors. The Journal of Pathology published by John Wiley & Sons, Ltd. on behalf of The Pathological Society of Great Britain and Ireland.