Recent application of artificial intelligence on histopathologic image-based prediction of gene mutation in solid cancers.

PURPOSE: Evaluation of genetic mutations in cancers is important because distinct mutational profiles help determine individualized drug therapy. However, molecular analyses are not routinely performed in all cancers because they are expensive, time-consuming and not universally available. Artificial intelligence (AI) has shown the potential to determine a wide range of genetic mutations on histologic image analysis. Here, we assessed the status of mutation prediction AI models on histologic images by a systematic review. METHODS: A literature search using the MEDLINE, Embase and Cochrane databases was conducted in August 2021. The articles were shortlisted by titles and abstracts. After a full-text review, publication trends, study characteristic analysis and comparison of performance metrics were performed. RESULTS: Twenty-four studies were found mostly from developed countries, and their number is increasing. The major targets were gastrointestinal, genitourinary, gynecological, lung and head and neck cancers. Most studies used the Cancer Genome Atlas, with a few using an in-house dataset. The area under the curve of some of the cancer driver gene mutations in particular organs was satisfactory, such as 0.92 of BRAF in thyroid cancers and 0.79 of EGFR in lung cancers, whereas the average of all gene mutations was 0.64, which is still suboptimal. CONCLUSION: AI has the potential to predict gene mutations on histologic images with appropriate caution. Further validation with larger datasets is still required before AI models can be used in clinical practice to predict gene mutations.

Two Cases of Lymph Node Metastasis Found in Differentiated, Small-Sized Gastric Adenocarcinomas: Did Tumor Budding Play a Critical Role?

Background: Endoscopic resection (ER) is a minimally invasive therapeutic approach for early gastric cancer (EGC), particularly for cases with a low risk of lymph node metastasis (LNM). Tumor budding (TB) has gained attention as a potential prognostic indicator for LNM in EGC. Case Presentation: We report two cases-a 73-year-old and an 81-year-old male patient-who presented with gastric adenocarcinoma. Both patients had small-sized, differentiated, and intramucosal adenocarcinomas. However, high-grade TBs per high-power field under ×200 magnification at the invasive front and LNMs were found in both cases. Conclusions: These cases conformed to the post-ER observation guidelines of the current treatment protocol, yet demonstrated LNMs. We found that TB could serve as an effective prognostic marker for LNM compared to traditional risk factors. The aim of this study is to re-examine the ability of TB to predict LNM in EGC, thereby providing an impetus for reconsideration and potential revision of the current treatment guidelines for EGC.

Intratumoral Budding in Pretreatment Biopsies, among Tumor Microenvironmental Components, Can Predict Prognosis and Neoadjuvant Therapy Response in Colorectal Adenocarcinoma.

Background and Objectives: The prediction of the prognosis and effect of neoadjuvant therapy is vital for patients with advanced or unresectable colorectal carcinoma (CRC). Materials and Methods: We investigated several tumor microenvironment factors, such as intratumoral budding (ITB), desmoplastic reaction (DR), and Klintrup-Mäkinen (KM) inflammation grade, and the tumor-stroma ratio (TSR) in pretreatment biopsy samples (PBSs) collected from patients with advanced or unresectable CRC. A total of 85 patients with 74 rectal carcinomas and 11 colon cancers treated at our hospital were enrolled; 66 patients had curative surgery and 19 patients received palliative treatment. Results: High-grade ITB was associated with recurrence (p = 0.002), death (p = 0.034), and cancer-specific death (p = 0.034). Immature DR was associated with a higher grade of clinical tumor-node-metastasis stage (cTNM) (p = 0.045), cN category (p = 0.045), and cM category (p = 0.046). The KM grade and TSR were not related to any clinicopathological factors. High-grade ITB had a significant relationship with tumor regression in patients who received curative surgery (p = 0.049). Conclusions: High-grade ITB in PBSs is a potential unfavorable prognostic factor for patients with advanced CRC. Immature DR, TSR, and KM grade could not predict prognosis or therapy response in PBSs.

Prognostic significance of stem cell/ epithelial-mesenchymal transition markers in periampullary/pancreatic cancers: FGFR1 is a promising prognostic marker.

BACKGROUND: Periampullary cancers (PAC) including pancreatic, ampulla of Vater (AOV), and common bile duct (CBD) cancers are highly aggressive with a lack of useful prognostic markers beyond T stage. However, T staging can be biased due to the anatomic complexity of this region. Recently, several markers related to cancer stem cells and epithelial-mesenchymal transition (EMT) such as octamer transcription factor-4 (Oct4) and fibroblast growth factor receptor 1 (FGFR1) respectively, have been proposed as new promising markers in other solid cancers. The aim of this study was to assess the expression and prognostic significance of stem cell/EMT markers in PACs. METHODS: Formalin-fixed, paraffin-embedded tissues of surgically excised PACs from the laboratory archives from 1998 to 2014 were evaluated by immunohistochemical staining for stem cell/EMT markers using tissue microarray. The clinicopathologic parameters were documented and statistically analyzed with the immunohistochemical findings. Survival and recurrence data were collected and analyzed. RESULTS: A total of 126 PAC cases were evaluated. The average age was 63 years, with 76 male and 50 female patient samples. Age less than 74 years, AOV cancers, lower T & N stage, lower tumor size, no lymphatic, vascular, perineural invasion and histologic well differentiation, intestinal type, no fibrosis, severe inflammation were significantly associated with the better overall survival High expression levels of FGFR1 as well as CK20, CDX2, and VEGF were significantly related to better overall survival, while other stem cell markers were not related. Similar findings were observed for tumor recurrence using disease-free survival. CONCLUSIONS: In addition to other clinicopathologic parameters, severe fibrosis was related to frequent tumor recurrence, and high FGFR1 expression was associated with better overall survival. Histologic changes such as extensive fibrosis need to be investigated further in relation to EMT of PACs.

Could -79 °C Spray-Type Cryotherapy Be an Effective Monotherapy for the Treatment of Keloid?

Cryotherapy has been regarded as an effective modality for the treatment of keloids, and the spray-type device is one of the novel cryotherapeutic units. However, the biological mechanisms and therapeutic effects of this technique are incompletely studied. We evaluated the clinical efficacy of our cryotherapy protocol with molecular and pathologic evidence for the treatment of keloids. We evenly split each of ten keloid lesions into a non-treated (C-) and treated (C+) area; the C+ area was subjected to two freeze-thaw cycles of spray-type cryotherapy using -79 °C spray-type CryoPen™. This treatment was repeated after an interval of two weeks. The proliferation and migration abilities of the fibroblasts isolated from the dermis under the cryotherapy-treated or untreated keloid tissues (at least 5 mm deep) were compared and pathologic findings of the full layer were evaluated. Molecular analysis revealed that the number of dermal fibroblasts was significantly higher in C+ group as compared with C- group. The dermal fibroblasts from C+ group showed more than two-fold increase in the migration ability as compared with the fibroblasts from C- group. The expression of matrix metallopeptidase 9 was increased by more than two-fold and a significant increase in transforming growth factor beta 1 expression and Smad2/3 phosphorylation level was observed in C+ group. C+ group showed more extensive lymphoplasmacytic infiltration with thicker fibrosis and occasional "proliferating core collagen" as compared with C- group. Thus, -79 °C spray-type cryotherapy is ineffective as a monotherapy and should be used in combination with intralesional corticosteroids or botulinum toxin A for favourable outcomes in the treatment of thick keloids.

Identification of a novel GLA mutation (Y88C) in a Korean family with Fabry nephropathy: a case report.

BACKGROUND: Fabry disease is a rare X-linked lysosomal storage disorder caused by α-galactosidase A deficiency. With the advancement of molecular diagnostic tools, more disease-causing mutations in α-galactosidase A (GLA) have been identified in Fabry disease. We found a novel mutation in a Korean family with predominant renal manifestations of the disease. CASE PRESENTATION: A 24-year-old man who wanted to donate a kidney to his 28-year-old brother with end-stage renal disease of unknown cause was evaluated. The 24-year-old man underwent percutaneous renal biopsy because of an accidentally found proteinuria. Electron microscopy of his renal biopsy showed numerous electron-dense multi-lamellar inclusions in the epithelial cytoplasm, typical for Fabry disease. Clinical and laboratory evaluation including the assessment of GLA enzyme activity and direct DNA sequencing in four members of the family were performed. Renal biopsy findings in the two affected male patients were described. Re-evaluation of a renal biopsy specimen of his 28-year-old brother obtained when he was diagnosed with renal failure revealed a very focal area of suspicious multilamellated structures in the Bowman's space. DNA sequencing on the young man, his brother, and his mother revealed a novel GLA gene mutation, c.263A > G (p.Tyr88Cys). The three all showed decreased α-galactosidase A activity. CONCLUSION: A novel GLA mutation, c.263A > G (p.Tyr88Cys), was found in a Korean family with predominant renal manifestations of Fabry disease.

Bilirubin provides perforator flap protection from ischaemia-reperfusion injury in a rat model: a preliminary result.

The use of bilirubin, a well-known and powerful antioxidant, has gained popularity in recent years because of its role in the prevention of ischaemic heart disease in patients with Gilbert's syndrome. We investigate the effects of bilirubin on ischaemia-reperfusion (I/R) injury using a rat perforator flap model. Forty-eight rats were randomly divided into two groups: experimental (bilirubin) group (n = 24) and control group (n = 24). In each group, elevated bilateral deep inferior epigastric perforator (DIEP) flaps were created. The right (no ischaemia side) and left (ischaemia side) DIEP flaps were separated according to the presence of ischaemia induction. Ischaemia was induced in anaesthetised rats by perforator clamping for 15 or 30 minutes. After surgery, the flap survival was assessed daily on postoperative days 0 to 5, and overall histological changes of DIEP flaps above the perforator were analysed at postoperative day 5. The flap survival rate in the bilirubin group was significantly higher than that in the control group at the ischaemia side following perforator clamping for 15 or 30 minutes (93·42 ± 4·48% versus 89·63 ± 3·98%, P = 0·002; and 83·96 ± 4·23% versus 36·46 ± 6·38%, P < 0·001, respectively). The difference in flap survival between the two groups was the most prominent on the ischaemic side following 30 minutes of perforator clamping. From a morphologic perspective, pre-treatment with bilirubin was found to alleviate perforator flap necrosis caused by I/R injury in this experimental rat model.

Histomorphometric analysis of collagen architecture of auricular keloids in an Asian population.

BACKGROUND: Keloids are a pathologic condition of the reparative process, which present as excessive scar formation that involves various cells and cytokines. Many studies focusing on the histologic feature of keloids, however, have shown discordant results without consideration of architectural aspect of collagen structure. OBJECTIVE: The purpose of this study was to demonstrate a schematic illustration of collagen architecture of keloids, specifically auricular keloids, and to analyze each part on the histomorphologic and morphometric basis. MATERIALS AND METHODS: Thirty-nine surgically excised auricular keloids were retrieved from the file of Kangbuk Samsung Hospital. After exhaustive histomorphologic analysis, 3 distinctive structural parts, keloidal collagen, organizing collagen, and proliferating core collagen, were identified and mapped in every case. Cellularity of fibroblasts, blood vessel density, degree of inflammatory cell infiltration, and mast cells counts using Masson trichrome stain, Van Gieson stain, toluidine blue stain, and immunohistochemical stains for CD31 and smooth muscle actin were analyzed in each part of each case. Morphometric analysis on these parameters using ImageJ software was performed using 3 representative images of each part. RESULTS: Three parts were histomorphologically distinct by shape and array of collagen bundles, fibroblasts cellularity, blood vessel density, degree of inflammatory cells, and mast cell infiltration. Morphometric analysis revealed statistically significant difference between each part in fibroblasts cellularity, blood vessel density, degree of inflammatory cell infiltration, and mast cells count. All parameters were exceedingly high in whorling hypercellular fibrous nodules in proliferating core collagen showing simultaneous changes in other parts. CONCLUSION: Morphologically and morphometrically, 3 distinctive parts were identified in auricular keloids. Mast cell infiltrations, blood vessel density, and fibroblast cellularity are simultaneously increased or decreased according to these parts. Proliferating core collagen might serve as a proliferating center of keloids and might be a key portion for tumor growth and recurrence.

The effects of botulinum toxin A on survival of rat TRAM flap with vertical midline scar.

The transverse rectus abdominis musculocutaneous (TRAM) flap has been widely used in various reconstructive surgeries. Recently, there have been reports regarding the positive effect of botulinum toxin A (BoTA) on flap survival. We hypothesized that pretreatment with BoTA could augment the survival of pedicled TRAM flaps with a vertical midline scar. Twenty-four Sprague-Dawley rats were randomly divided into 2 groups, namely, control group and BoTA group. Five days after a vertical midline incision, the BoTA group was pretreated with BoTA, whereas the control group was pretreated with normal saline. Ten days after the initial incision, the TRAM flap was harvested. We evaluated the gross flap survival and analyzed the overall histologic change, lumen area of pedicle, and microvessel density with immunohistochemistry. Reverse transcription polymerase chain reaction was performed for the evaluation of angiogenesis-related factors. In the BoTA group, the gross flap survival rate was significantly higher than that in the control group on both ipsilateral and contralateral sides (P < 0.001). In the BoTA group, a significant increase in pedicle lumen area was observed (P < 0.001). In the control group, mild to moderate epidermal necrosis was seen; microvessels were relatively small compared with those of the BoTA group. According to immunohistochemistry, the number of CD31 positively stained vessels was significantly higher on the contralateral side in the control group compared to that in the BoTA group (P < 0.001). The relative messenger RNA (mRNA) expression of CD31 was significantly lower in the BoTA group than that in the control group on both ipsilateral and contralateral sides (P < 0.001). Meanwhile, the relative mRNA expression of VEGF was significantly higher in the BoTA group than in the control group on both ipsilateral and contralateral sides (P < 0.001).We believe that preoperative BoTA therapy is a feasible method to improve circulation of the rat TRAM flap with a vertical midline incision scar.

Lipofibromatous hamartoma of a cranial nerve.

Lipofibromatous hamartomas (LFHs) are rare benign tumors that typically present as slow-growing firm masses in the subcutaneous soft tissue of the extremities. These often develop in young adults on the volar aspects of the hands, wrists, and forearms along major nerves and their branches. Only a single case of LFH growth along a cranial nerve has been reported. A 41-year-old man presented with a subcutaneous soft mass of the cheek. Histologically, the mass consisted of a proliferating fibrofatty tissue that surrounded and infiltrated the nerve structure and it was confirmed to be an LFH. After surgical excision, the patient experienced mild facial numbness and motor disturbance on the side ipsilateral to the resection. Because complete excision of the mass can cause sensory or motor disturbances, an accurate diagnosis and proper subsequent treatment, such as partial decompression, are necessary.

Immunoglobulin G4-related disease mimicking an appendiceal neoplasm: a case report.

Immunoglobulin G4-related disease (IgG4-RD) is a fibroinflammatory condition characterized by chronic activation of the immune system and a tendency to form tumorous lesions. IgG4-RD is frequently characterized by the presence of tumor-like masses affecting multiple organs and is easily mistaken for a malignant neoplasm. However, IgG4-RD affecting the appendix is extremely rare, with only seven cases reported previously. We report the case of a woman in her early 60s who presented with insidious abdominal pain and radiological findings mimicking appendiceal neoplasms. After diagnosing appendiceal neoplasms, surgery was performed. The patient had a serum IgG4 concentration of <1.35 g/L, which did not satisfy one of the three revised comprehensive diagnostic criteria for IgG4-RD. A pathological examination was conducted, and the patient was diagnosed with appendiceal IgG4-RD. To the best of our knowledge, there have been no previously reported cases of IgG4-RD affecting the appendix in patients with low serum IgG4 concentrations. This report may prove beneficial for the future understanding of IgG4-RD and for the revision of diagnostic and treatment strategies.

Poly (ADP-ribose) polymerase-1 (PARP-1) is a good prognostic marker for pancreatic/periampullary cancers.

BACKGROUND: Periampullary cancer (PAC) is highly aggressive with no effective adjuvant therapy or prognostic markers. Recently, poly (ADP-ribose) polymerases-1 (PARP-1) have emerged as a target in solid cancers, and its relationship with epithelial-mesenchymal transition (EMT) has been observed. However, the relationship between PARP-1 and EMT in PAC has not explored well. METHODS: We assessed the prognostic significance of PARP1 in 190 PACs patients and correlated it with EMT markers, including FGF8, FGFR4, MMP2, MMP3, Snail, and ZEB1. Immunohistochemistry for PARP-1 and EMT markers was performed using a tissue microarray. RESULTS: PARP-1 and FGF8 expression were associated with better survival unlike other solid cancers (P = 0.006 and P = 0.003), and MMP3 and ZEB1 expression were associated with poor prognosis in multivariate and survival analyses (P = 0.009 and P < 0.001). In addition, PARP-1 is related negatively to Snail but not related with other EMT markers, implying an independent mechanism between PARP-1 and EMT in PACs. PARP-1 and FGF8 are independent good survival markers in PACs unlike other solid cancers. CONCLUSIONS: PARP-1 and FGF8 in PACs could not be related to the EMT pathway but must be rather understood in light of similar cancer-protective roles. Further studies are required on EMT-associated immune markers in PACs.

Artificial-Intelligence-Assisted Detection of Metastatic Colorectal Cancer Cells in Ascitic Fluid.

Ascites cytology is a cost-effective test for metastatic colorectal cancer (CRC) in the abdominal cavity. However, metastatic carcinoma of the peritoneum is difficult to diagnose based on biopsy findings, and ascitic aspiration cytology has a low sensitivity and specificity and a high inter-observer variability. The aim of the present study was to apply artificial intelligence (AI) to classify benign and malignant cells in ascites cytology patch images of metastatic CRC using a deep convolutional neural network. Datasets were collected from The OPEN AI Dataset Project, a nationwide cytology dataset for AI research. The numbers of patch images used for training, validation, and testing were 56,560, 7068, and 6534, respectively. We evaluated 1041 patch images of benign and metastatic CRC in the ascitic fluid to compare the performance of pathologists and an AI algorithm, and to examine whether the diagnostic accuracy of pathologists improved with the assistance of AI. This AI method showed an accuracy, a sensitivity, and a specificity of 93.74%, 87.76%, and 99.75%, respectively, for the differential diagnosis of malignant and benign ascites. The diagnostic accuracy and sensitivity of the pathologist with the assistance of the proposed AI method increased from 86.8% to 90.5% and from 73.3% to 79.3%, respectively. The proposed deep learning method may assist pathologists with different levels of experience in diagnosing metastatic CRC cells of ascites.

Improved Diagnostic Accuracy of Thyroid Fine-Needle Aspiration Cytology with Artificial Intelligence Technology.

Background: Artificial intelligence (AI) is increasingly being applied in pathology and cytology, showing promising results. We collected a large dataset of whole slide images (WSIs) of thyroid fine-needle aspiration cytology (FNA), incorporating z-stacking, from institutions across the nation to develop an AI model. Methods: We conducted a multicenter retrospective diagnostic accuracy study using thyroid FNA dataset from the Open AI Dataset Project that consists of digitalized images samples collected from 3 university hospitals and 215 Korean institutions through extensive quality check during the case selection, scanning, labeling, and reviewing process. Multiple z-layer images were captured using three different scanners and image patches were extracted from WSIs and resized after focus fusion and color normalization. We pretested six AI models, determining Inception ResNet v2 as the best model using a subset of dataset, and subsequently tested the final model with total datasets. Additionally, we compared the performance of AI and cytopathologists using randomly selected 1031 image patches and reevaluated the cytopathologists' performance after reference to AI results. Results: A total of 10,332 image patches from 306 thyroid FNAs, comprising 78 malignant (papillary thyroid carcinoma) and 228 benign from 86 institutions were used for the AI training. Inception ResNet v2 achieved highest accuracy of 99.7%, 97.7%, and 94.9% for training, validation, and test dataset, respectively (sensitivity 99.9%, 99.6%, and 100% and specificity 99.6%, 96.4%, and 90.4% for training, validation, and test dataset, respectively). In the comparison between AI and human, AI model showed higher accuracy and specificity than the average expert cytopathologists beyond the two-standard deviation (accuracy 99.71% [95% confidence interval (CI), 99.38-100.00%] vs. 88.91% [95% CI, 86.99-90.83%], sensitivity 99.81% [95% CI, 99.54-100.00%] vs. 87.26% [95% CI, 85.22-89.30%], and specificity 99.61% [95% CI, 99.23-99.99%] vs. 90.58% [95% CI, 88.80-92.36%]). Moreover, after referring to the AI results, the performance of all the experts (accuracy 96%, 95%, and 96%, respectively) and the diagnostic agreement (from 0.64 to 0.84) increased. Conclusions: These results suggest that the application of AI technology to thyroid FNA cytology may improve the diagnostic accuracy as well as intra- and inter-observer variability among pathologists. Further confirmatory research is needed.

Validation of a Machine Learning Expert Supporting System, ImmunoGenius, Using Immunohistochemistry Results of 3000 Patients with Lymphoid Neoplasms.

(1) Background: Differential diagnosis using immunohistochemistry (IHC) panels is a crucial step in the pathological diagnosis of hematolymphoid neoplasms. In this study, we evaluated the prediction accuracy of the ImmunoGenius software using nationwide data to validate its clinical utility. (2) Methods: We collected pathologically confirmed lymphoid neoplasms and their corresponding IHC results from 25 major university hospitals in Korea between 2015 and 2016. We tested ImmunoGenius using these real IHC panel data and compared the precision hit rate with previously reported diagnoses. (3) Results: We enrolled 3052 cases of lymphoid neoplasms with an average of 8.3 IHC results. The precision hit rate was 84.5% for these cases, whereas it was 95.0% for 984 in-house cases. (4) Discussion: ImmunoGenius showed excellent results in most B-cell lymphomas and generally showed equivalent performance in T-cell lymphomas. The primary reasons for inaccurate precision were atypical IHC profiles of certain cases, lack of disease-specific markers, and overlapping IHC profiles of similar diseases. We verified that the machine-learning algorithm could be applied for diagnosis precision with a generally acceptable hit rate in a nationwide dataset. Clinical and histological features should also be taken into account for the proper use of this system in the decision-making process.

Diagnostic proficiency test using digital cytopathology and comparative assessment of whole slide images of cytologic samples for quality assurance program in Korea.

BACKGROUND: The Korean Society for Cytopathology introduced a digital proficiency test (PT) in 2021. However, many doubtful opinions remain on whether digitally scanned images can satisfactorily present subtle differences in the nuclear features and chromatin patterns of cytological samples. METHODS: We prepared 30 whole-slide images (WSIs) from the conventional PT archive by a selection process for digital PT. Digital and conventional PT were performed in parallel for volunteer institutes, and the results were compared using feedback. To assess the quality of cytological assessment WSIs, 12 slides were collected and scanned using five different scanners, with four cytopathologists evaluating image quality through a questionnaire. RESULTS: Among the 215 institutes, 108 and 107 participated in glass and digital PT, respectively. No significant difference was noted in category C (major discordance), although the number of discordant cases was slightly higher in the digital PT group. Leica, 3DHistech Pannoramic 250 Flash, and Hamamatsu NanoZoomer 360 systems showed comparable results in terms of image quality, feature presentation, and error rates for most cytological samples. Overall satisfaction was observed with the general convenience and image quality of digital PT. CONCLUSIONS: As three-dimensional clusters are common and nuclear/chromatin features are critical for cytological interpretation, careful selection of scanners and optimal conditions are mandatory for the successful establishment of digital quality assurance programs in cytology.

Uterine Cervical Angioleiomyoma Mimicking Squamous Cell Carcinoma.

Angioleiomyoma, a rare variant of leiomyoma, is a benign tumor of mesenchymal origin. Angioleiomyomas of the female urogenital tract are extremely rare, with only six cases of uterine cervical angioleiomyoma previously reported in the literature. In this case study, we report on a 49-year-old female patient who presented with menorrhagia whose initial magnetic resonance imaging (MRI) findings suggested cervical squamous cell carcinoma (SCC). However, following the hysterectomy, histological examination confirmed the lesion to be angioleiomyoma. To the best of our knowledge, there have been no previously reported cases of angioleiomyomas presenting with MRI findings that are suggestive of uterine SCC. Recognizing that angioleiomyomas can mimic uterine malignancies on MRI may prove beneficial for future diagnostic and treatment strategies.

A stepwise approach to fine needle aspiration cytology of lymph nodes.

The cytological diagnosis of lymph node lesions is extremely challenging because of the diverse diseases that cause lymph node enlargement, including both benign and malignant or metastatic lymphoid lesions. Furthermore, the cytological findings of different lesions often resemble one another. A stepwise diagnostic approach is essential for a comprehensive diagnosis that combines: clinical findings, including age, sex, site, multiplicity, and ultrasonography findings; low-power reactive, metastatic, and lymphoma patterns; high-power population patterns, including two populations of continuous range, small monotonous pattern and large monotonous pattern; and disease-specific diagnostic clues including granulomas and lymphoglandular granules. It is also important to remember the histological features of each diagnostic category that are common in lymph node cytology and to compare them with cytological findings. It is also essential to identify a few categories of diagnostic pitfalls that often resemble lymphomas and easily lead to misdiagnosis, particularly in malignant small round cell tumors, poorly differentiated squamous cell carcinomas, and nasopharyngeal undifferentiated carcinoma. Herein, we review a stepwise approach for fine needle aspiration cytology of lymphoid diseases and suggest a diagnostic algorithm that uses this approach and the Sydney classification system.

Deep Learning-Based Computational Cytopathologic Diagnosis of Metastatic Breast Carcinoma in Pleural Fluid.

A Pleural effusion cytology is vital for treating metastatic breast cancer; however, concerns have arisen regarding the low accuracy and inter-observer variability in cytologic diagnosis. Although artificial intelligence-based image analysis has shown promise in cytopathology research, its application in diagnosing breast cancer in pleural fluid remains unexplored. To overcome these limitations, we evaluate the diagnostic accuracy of an artificial intelligence-based model using a large collection of cytopathological slides, to detect the malignant pleural effusion cytology associated with breast cancer. This study includes a total of 569 cytological slides of malignant pleural effusion of metastatic breast cancer from various institutions. We extracted 34,221 augmented image patches from whole-slide images and trained and validated a deep convolutional neural network model (DCNN) (Inception-ResNet-V2) with the images. Using this model, we classified 845 randomly selected patches, which were reviewed by three pathologists to compare their accuracy. The DCNN model outperforms the pathologists by demonstrating higher accuracy, sensitivity, and specificity compared to the pathologists (81.1% vs. 68.7%, 95.0% vs. 72.5%, and 98.6% vs. 88.9%, respectively). The pathologists reviewed the discordant cases of DCNN. After re-examination, the average accuracy, sensitivity, and specificity of the pathologists improved to 87.9, 80.2, and 95.7%, respectively. This study shows that DCNN can accurately diagnose malignant pleural effusion cytology in breast cancer and has the potential to support pathologists.

Deep learning-based diagnosis of lung cancer using a nationwide respiratory cytology image set: improving accuracy and inter-observer variability.

Deep learning (DL)-based image analysis has recently seen widespread application in digital pathology. Recent studies utilizing DL in cytopathology have shown promising results, however, the development of DL models for respiratory specimens is limited. In this study, we designed a DL model to improve lung cancer diagnosis accuracy using cytological images from the respiratory tract. This retrospective, multicenter study used digital cytology images of respiratory specimens from a quality-controlled national dataset collected from over 200 institutions. The image processing involves generating extended z-stack images to reduce the phase difference of cell clusters, color normalizing, and cropping image patches to 256 × 256 pixels. The accuracy of diagnosing lung cancer in humans from image patches before and after receiving AI assistance was compared. 30,590 image patches (1,273 whole slide images [WSIs]) were divided into 27,362 (1,146 WSIs) for training, 2,928 (126 WSIs) for validation, and 1,272 (1,272 WSIs) for testing. The Densenet121 model, which showed the best performance among six convolutional neural network models, was used for analysis. The results of sensitivity, specificity, and accuracy were 95.9%, 98.2%, and 96.9% respectively, outperforming the average of three experienced pathologists. The accuracy of pathologists after receiving AI assistance improved from 82.9% to 95.9%, and the inter-rater agreement of Fleiss' Kappa value was improved from 0.553 to 0.908. In conclusion, this study demonstrated that a DL model was effective in diagnosing lung cancer in respiratory cytology. By increasing diagnostic accuracy and reducing inter-observer variability, AI has the potential to enhance the diagnostic capabilities of pathologists.