Artificial intelligence in medicine: mitigating risks and maximizing benefits via quality assurance, quality control, and acceptance testing.

The adoption of artificial intelligence (AI) tools in medicine poses challenges to existing clinical workflows. This commentary discusses the necessity of context-specific quality assurance (QA), emphasizing the need for robust QA measures with quality control (QC) procedures that encompass (1) acceptance testing (AT) before clinical use, (2) continuous QC monitoring, and (3) adequate user training. The discussion also covers essential components of AT and QA, illustrated with real-world examples. We also highlight what we see as the shared responsibility of manufacturers or vendors, regulators, healthcare systems, medical physicists, and clinicians to enact appropriate testing and oversight to ensure a safe and equitable transformation of medicine through AI.

Analysis of domain shift in whole prostate gland, zonal and lesions segmentation and detection, using multicentric retrospective data.

Despite being one of the most prevalent forms of cancer, prostate cancer (PCa) shows a significantly high survival rate, provided there is timely detection and treatment. Computational methods can help make this detection process considerably faster and more robust. However, some modern machine-learning approaches require accurate segmentation of the prostate gland and the index lesion. Since performing manual segmentations is a very time-consuming task, and highly prone to inter-observer variability, there is a need to develop robust semi-automatic segmentation models. In this work, we leverage the large and highly diverse ProstateNet dataset, which includes 638 whole gland and 461 lesion segmentation masks, from 3 different scanner manufacturers provided by 14 institutions, in addition to other 3 independent public datasets, to train accurate and robust segmentation models for the whole prostate gland, zones and lesions. We show that models trained on large amounts of diverse data are better at generalizing to data from other institutions and obtained with other manufacturers, outperforming models trained on single-institution single-manufacturer datasets in all segmentation tasks. Furthermore, we show that lesion segmentation models trained on ProstateNet can be reliably used as lesion detection models.

Development and validation of a clinical decision support system based on PSA, microRNAs, and MRI for the detection of prostate cancer.

OBJECTIVES: The aims of this study are to develop and validate a clinical decision support system based on demographics, prostate-specific antigen (PSA), microRNA (miRNA), and MRI for the detection of prostate cancer (PCa) and clinical significant (cs) PCa, and to assess if this system performs better compared to MRI alone. METHODS: This retrospective, multicenter, observational study included 222 patients (mean age 66, range 46-75 years) who underwent prostate MRI, miRNA (let-7a-5p and miR-103a-3p) assessment, and biopsy. Monoparametric and multiparametric models including age, PSA, miRNA, and MRI outcome were trained on 65% of the data and then validated on the remaining 35% to predict both PCa (any Gleason grade [GG]) and csPCa (GG ≥ 2 vs GG = 1/negative). Accuracy, sensitivity, specificity, positive and negative predictive value (NPV), and area under the receiver operating characteristic curve were calculated. RESULTS: MRI outcome was the best predictor in the monoparametric model for both detection of PCa, with sensitivity of 90% (95%CI 73-98%) and NPV of 93% (95%CI 82-98%), and for csPCa identification, with sensitivity of 91% (95%CI 72-99%) and NPV of 95% (95%CI 84-99%). Sensitivity and NPV of PSA + miRNA for the detection of csPCa were not statistically different from the other models including MRI alone. CONCLUSION: MRI stand-alone yielded the best prediction models for both PCa and csPCa detection in biopsy-naïve patients. The use of miRNAs let-7a-5p and miR-103a-3p did not improve classification performances compared to MRI stand-alone results. CLINICAL RELEVANCE STATEMENT: The use of miRNA (let-7a-5p and miR-103a-3p), PSA, and MRI in a clinical decision support system (CDSS) does not improve MRI stand-alone performance in the detection of PCa and csPCa. KEY POINTS: • Clinical decision support systems including MRI improve the detection of both prostate cancer and clinically significant prostate cancer with respect to PSA test and/or microRNA. • The use of miRNAs let-7a-5p and miR-103a-3p did not significantly improve MRI stand-alone performance. • Results of this study were in line with previous works on MRI and microRNA.

Development and Validation of an Explainable Radiomics Model to Predict High-Aggressive Prostate Cancer: A Multicenter Radiomics Study Based on Biparametric MRI.

In the last years, several studies demonstrated that low-aggressive (Grade Group (GG) ≤ 2) and high-aggressive (GG ≥ 3) prostate cancers (PCas) have different prognoses and mortality. Therefore, the aim of this study was to develop and externally validate a radiomic model to noninvasively classify low-aggressive and high-aggressive PCas based on biparametric magnetic resonance imaging (bpMRI). To this end, 283 patients were retrospectively enrolled from four centers. Features were extracted from apparent diffusion coefficient (ADC) maps and T2-weighted (T2w) sequences. A cross-validation (CV) strategy was adopted to assess the robustness of several classifiers using two out of the four centers. Then, the best classifier was externally validated using the other two centers. An explanation for the final radiomics signature was provided through Shapley additive explanation (SHAP) values and partial dependence plots (PDP). The best combination was a naïve Bayes classifier trained with ten features that reached promising results, i.e., an area under the receiver operating characteristic (ROC) curve (AUC) of 0.75 and 0.73 in the construction and external validation set, respectively. The findings of our work suggest that our radiomics model could help distinguish between low- and high-aggressive PCa. This noninvasive approach, if further validated and integrated into a clinical decision support system able to automatically detect PCa, could help clinicians managing men with suspicion of PCa.

MI-Common Data Model: Extending Observational Medical Outcomes Partnership-Common Data Model (OMOP-CDM) for Registering Medical Imaging Metadata and Subsequent Curation Processes.

PURPOSE: The explosion of big data and artificial intelligence has rapidly increased the need for integrated, homogenized, and harmonized health data. Many common data models (CDMs) and standard vocabularies have appeared in an attempt to offer harmonized access to the available information, with Observational Medical Outcomes Partnership (OMOP)-CDM being one of the most prominent ones, allowing the standardization and harmonization of health care information. However, despite its flexibility, still capturing imaging metadata along with the corresponding clinical data continues to pose a challenge. This challenge arises from the absence of a comprehensive standard representation for image-related information and subsequent image curation processes and their interlinkage with the respective clinical information. Successful resolution of this challenge holds the potential to enable imaging and clinical data to become harmonized, quality-checked, annotated, and ready to be used in conjunction, in the development of artificial intelligence models and other data-dependent use cases. METHODS: To address this challenge, we introduce medical imaging (MI)-CDM-an extension of the OMOP-CDM specifically designed for registering medical imaging data and curation-related processes. Our modeling choices were the result of iterative numerous discussions among clinical and AI experts to enable the integration of imaging and clinical data in the context of the ProCAncer-I project, for answering a set of clinical questions across the prostate cancer's continuum. RESULTS: Our MI-CDM extension has been successfully implemented for the use case of prostate cancer for integrating imaging and curation metadata along with clinical information by using the OMOP-CDM and its oncology extension. CONCLUSION: By using our proposed terminologies and standardized attributes, we demonstrate how diverse imaging modalities can be seamlessly integrated in the future.

A European Society of Oncologic Imaging (ESOI) survey on the radiological assessment of response to oncologic treatments in clinical practice.

OBJECTIVES: To present the results of a survey on the assessment of treatment response with imaging in oncologic patient, in routine clinical practice. The survey was promoted by the European Society of Oncologic Imaging to gather information for the development of reporting models and recommendations. METHODS: The survey was launched on the European Society of Oncologic Imaging website and was available for 3 weeks. It consisted of 5 sections, including 24 questions related to the following topics: demographic and professional information, methods for lesion measurement, how to deal with diminutive lesions, how to report baseline and follow-up examinations, which previous studies should be used for comparison, and role of RECIST 1.1 criteria in the daily clinical practice. RESULTS: A total of 286 responses were received. Most responders followed the RECIST 1.1 recommendations for the measurement of target lesions and lymph nodes and for the assessment of tumor response. To assess response, 48.6% used previous and/or best response study in addition to baseline, 25.2% included the evaluation of all main time points, and 35% used as the reference only the previous study. A considerable number of responders used RECIST 1.1 criteria in daily clinical practice (41.6%) or thought that they should be always applied (60.8%). CONCLUSION: Since standardized criteria are mainly a prerogative of clinical trials, in daily routine, reporting strategies are left to radiologists and oncologists, which may issue local and diversified recommendations. The survey emphasizes the need for more generally applicable rules for response assessment in clinical practice. CRITICAL RELEVANCE STATEMENT: Compared to clinical trials which use specific criteria to evaluate response to oncological treatments, the free narrative report usually adopted in daily clinical practice may lack clarity and useful information, and therefore, more structured approaches are needed. KEY POINTS: · Most radiologists consider standardized reporting strategies essential for an objective assessment of tumor response in clinical practice. · Radiologists increasingly rely on RECIST 1.1 in their daily clinical practice. · Treatment response evaluation should require a complete analysis of all imaging time points and not only of the last.

Could normalization improve robustness of abdominal MRI radiomic features?

Radiomics-based systems could improve the management of oncological patients by supporting cancer diagnosis, treatment planning, and response assessment. However, one of the main limitations of these systems is the generalizability and reproducibility of results when they are applied to images acquired in different hospitals by different scanners. Normalization has been introduced to mitigate this issue, and two main approaches have been proposed: one rescales the image intensities (image normalization), the other the feature distributions for each center (feature normalization). The aim of this study is to evaluate how different image and feature normalization methods impact the robustness of 93 radiomics features acquired using a multicenter and multi-scanner abdominal Magnetic Resonance Imaging (MRI) dataset. To this scope, 88 rectal MRIs were retrospectively collected from 3 different institutions (4 scanners), and for each patient, six 3D regions of interest on the obturator muscle were considered. The methods applied were min-max, 1st-99th percentiles and 3-Sigma normalization, z-score standardization, mean centering, histogram normalization, Nyul-Udupa and ComBat harmonization. The Mann-Whitney U-test was applied to assess features repeatability between scanners, by comparing the feature values obtained for each normalization method, including the case in which no normalization was applied. Most image normalization methods allowed to reduce the overall variability in terms of intensity distributions, while worsening or showing unpredictable results in terms of feature robustness, except for thez-score, which provided a slight improvement by increasing the number of statistically similar features from 9/93 to 10/93. Conversely, feature normalization methods positively reduced the overall variability across the scanners, in particular, 3sigma,z_scoreandComBatthat increased the number of similar features (79/93). According to our results, it emerged that none of the image normalization methods was able to strongly increase the number of statistically similar features.

A mutation-based radiomics signature predicts response to imatinib in Gastrointestinal Stromal Tumors (GIST).

Objectives: To develop a mutation-based radiomics signature to predict response to imatinib in Gastrointestinal Stromal Tumors (GISTs). Methods: Eighty-two patients with GIST were enrolled in this retrospective study, including 52 patients from one center that were used to develop the model, and 30 patients from a second center to validate it. Reference standard was the mutational status of tyrosine-protein kinase (KIT) and platelet-derived growth factor α (PDGFRA). Patients were dichotomized in imatinib sensitive (group 0 - mutation in KIT or PDGFRA, different from exon 18-D842V), and imatinib non-responsive (group 1 - PDGFRA exon 18-D842V mutation or absence of mutation in KIT/PDGFRA). Initially, 107 texture features were extracted from the tumor masks of baseline computed tomography scans. Different machine learning methods were then implemented to select the best combination of features for the development of the radiomics signature. Results: The best performance was obtained with the 5 features selected by the ANOVA model and the Bayes classifier, using a threshold of 0.36. With this setting the radiomics signature had an accuracy and precision for sensitive patients of 82 % (95 % CI:60-95) and 90 % (95 % CI:73-97), respectively. Conversely, a precision of 80 % (95 % CI:34-97) was obtained in non-responsive patients using a threshold of 0.9. Indeed, with the latter setting 4 patients out of 5 were correctly predicted as non-responders. Conclusions: The results are a first step towards using radiomics to improve the management of patients with GIST, especially when tumor tissue is unavailable for molecular analysis or when molecular profiling is inconclusive.

Virtual biopsy in abdominal pathology: where do we stand?

In recent years, researchers have explored new ways to obtain information from pathological tissues, also exploring non-invasive techniques, such as virtual biopsy (VB). VB can be defined as a test that provides promising outcomes compared to traditional biopsy by extracting quantitative information from radiological images not accessible through traditional visual inspection. Data are processed in such a way that they can be correlated with the patient's phenotypic expression, or with molecular patterns and mutations, creating a bridge between traditional radiology, pathology, genomics, and artificial intelligence (AI). Radiomics is the backbone of VB, since it allows the extraction and selection of features from radiological images, feeding them into AI models in order to derive lesions' pathological characteristics and molecular status. Presently, the output of VB provides only a gross approximation of the findings of tissue biopsy. However, in the future, with the improvement of imaging resolution and processing techniques, VB could partially substitute the classical surgical or percutaneous biopsy, with the advantage of being non-invasive, comprehensive, accounting for lesion heterogeneity, and low cost. In this review, we investigate the concept of VB in abdominal pathology, focusing on its pipeline development and potential benefits.

Arthrogryposis multiplex congenita with maxillofacial involvement: a case report.

BACKGROUND: Arthrogryposis multiplex congenita is a rare condition that mainly involves the lower limbs, characterized by severe joint deformity and contracture, muscular atrophy, and functional impairment. Its clinical manifestations are heterogenous and may involve the maxillofacial district as well. CASE PRESENTATION: This case report describes a 20-year-old patient with arthrogryposis multiplex congenita with skeletal crossbite, facial asymmetry, reduced mouth opening and absence of lateral mandibular movement on the left side. After clinical evaluation, the following exams were required: postero-anterior cephalometric tracing, head and neck electromyography, computerized axiography, computed tomography scan, and maxillofacial magnetic resonance imaging. Orthognathodontic evaluation indicated skeletal asymmetry, reduced condylar movements on the left side and abnormally low electromyography activity of the masticatory muscles on the left side. Computed tomography and magnetic resonance imaging revealed unilateral left mandibular hypoplasia, hypotrophy, and fatty infiltration of masticatory muscles on the left side, as well as immobility of the left condyle during mouth opening, and hypoplasia of the left articular disk, which was however not displaced. Surgery was not indicated and conservative orthognathodontic treatment with function generating bite was suggested to balance the occlusal plane, as well as stretching exercises. CONCLUSIONS: A rare case of arthrogryposis multiplex congenita with maxillofacial involvement illustrates that a patient-centred, multidisciplinary approach with accurate diagnosis is required to formulate the best treatment plan. Because of the considerable damage to the masticatory muscles, conservative orthognathodontic therapy may be the best treatment option.

AAPM task group report 273: Recommendations on best practices for AI and machine learning for computer-aided diagnosis in medical imaging.

Rapid advances in artificial intelligence (AI) and machine learning, and specifically in deep learning (DL) techniques, have enabled broad application of these methods in health care. The promise of the DL approach has spurred further interest in computer-aided diagnosis (CAD) development and applications using both "traditional" machine learning methods and newer DL-based methods. We use the term CAD-AI to refer to this expanded clinical decision support environment that uses traditional and DL-based AI methods. Numerous studies have been published to date on the development of machine learning tools for computer-aided, or AI-assisted, clinical tasks. However, most of these machine learning models are not ready for clinical deployment. It is of paramount importance to ensure that a clinical decision support tool undergoes proper training and rigorous validation of its generalizability and robustness before adoption for patient care in the clinic. To address these important issues, the American Association of Physicists in Medicine (AAPM) Computer-Aided Image Analysis Subcommittee (CADSC) is charged, in part, to develop recommendations on practices and standards for the development and performance assessment of computer-aided decision support systems. The committee has previously published two opinion papers on the evaluation of CAD systems and issues associated with user training and quality assurance of these systems in the clinic. With machine learning techniques continuing to evolve and CAD applications expanding to new stages of the patient care process, the current task group report considers the broader issues common to the development of most, if not all, CAD-AI applications and their translation from the bench to the clinic. The goal is to bring attention to the proper training and validation of machine learning algorithms that may improve their generalizability and reliability and accelerate the adoption of CAD-AI systems for clinical decision support.

Use of information and communication technologies (ICTs) in cancer multidisciplinary team meetings: an explorative study based on EU healthcare professionals.

OBJECTIVES: Multidisciplinary teams in cancer care are increasingly using information and communication technology (ICT), hospital health information system (HIS) functionalities and ICT-driven care components. We aimed to explore the use of these tools in multidisciplinary team meetings (MTMs) and to identify the critical challenges posed by their adoption based on the perspective of professionals representatives from European scientific societies. DESIGN: This qualitative study used discussion of cases and focus group technique to generate data. Thematic analysis was applied. SETTING: Healthcare professionals working in a multidisciplinary cancer care environment. PARTICIPANTS: Selection of informants was carried out by European scientific societies in accordance with professionals' degree of experience in adopting the implementation of ICT and from different health systems. RESULTS: Professionals representatives of 9 European scientific societies were involved. Up to 10 ICTs, HIS functionalities and care components are embedded in the informational and decision-making processes along three stages of MTMs. ICTs play a key role in opening MTMs to other institutions (eg, by means of molecular tumour boards) and information types (eg, patient-reported outcome measures), and in contributing to the internal efficiency of teams. While ICTs and care components have their own challenges, the information technology context is characterised by the massive generation of unstructured data, the lack of interoperability between systems from different hospitals and HIS that are conceived to store and classify information rather than to work with it. CONCLUSIONS: The emergence of an MTM model that is better integrated in the wider health system context and incorporates inputs from patients and support systems make traditional meetings more dynamic and interconnected. Although these changes signal a second transition in the development process of multidisciplinary teams, they occur in a context marked by clear gaps between the information and management needs of MTMs and the adequacy of current HIS.

Imaging standardisation in metastatic colorectal cancer: A joint EORTC-ESOI-ESGAR expert consensus recommendation.

BACKGROUND: Treatment monitoring in metastatic colorectal cancer (mCRC) relies on imaging to evaluate the tumour burden. Response Evaluation Criteria in Solid Tumors provide a framework on reporting and interpretation of imaging findings yet offer no guidance on a standardised imaging protocol tailored to patients with mCRC. Imaging protocol heterogeneity remains a challenge for the reproducibility of conventional imaging end-points and is an obstacle for research on novel imaging end-points. PATIENTS AND METHODS: Acknowledging the recently highlighted potential of radiomics and artificial intelligence tools as decision support for patient care in mCRC, a multidisciplinary, international and expert panel of imaging specialists was formed to find consensus on mCRC imaging protocols using the Delphi method. RESULTS: Under the guidance of the European Organisation for Research and Treatment of Cancer (EORTC) Imaging and Gastrointestinal Tract Cancer Groups, the European Society of Oncologic Imaging (ESOI) and the European Society of Gastrointestinal and Abdominal Radiology (ESGAR), the EORTC-ESOI-ESGAR core imaging protocol was identified. CONCLUSION: This consensus protocol attempts to promote standardisation and to diminish variations in patient preparation, scan acquisition and scan reconstruction. We anticipate that this standardisation will increase reproducibility of radiomics and artificial intelligence studies and serve as a catalyst for future research on imaging end-points. For ongoing and future mCRC trials, we encourage principal investigators to support the dissemination of these imaging standards across recruiting centres.

A fully automatic deep learning algorithm to segment rectal Cancer on MR images: a multi-center study.

The aim of the study is to present and tune a fully automatic deep learning algorithm to segment colorectal cancers (CRC) on MR images, based on a U-Net structure. It is a multicenter study, including 3 different Italian institutions, that used 4 different MRI scanners. Two of them were used for training and tuning the systems, while the other two for the validation. The implemented algorithm consists of a pre-processing step to normalize and to highlight the tumoral area, followed by the CRC segmentation using different U-net structures. Automatic masks were compared with manual segmentations performed by three experienced radiologists, one at each center. The two best performing systems (called mdl2 and mdl3), obtained a median Dice Similarity Coefficient of 0.68(mdl2) - 0.69(mdl3), precision of 0.75(md/2) - 0.71(md/3), and recall of 0.69(mdl2) - 0.73(mdl3) on the validation set. Both systems reached high detection rates, 0.98 and 0.95, respectively, on the validation set. These encouraging results, if confirmed on larger dataset, might improve the management of patients with CRC, since it can be used as a fast and precise tool for further radiomics analyses. Clinical Relevance - To provide a reliable tool able to automatically segment CRC tumors that can be used as first step in future radiomics studies aimed at predicting response to chemotherapy and personalizing treatment.

Circulating tumor DNA to guide rechallenge with panitumumab in metastatic colorectal cancer: the phase 2 CHRONOS trial.

Anti-epidermal growth factor receptor (EGFR) monoclonal antibodies are approved for the treatment of RAS wild-type (WT) metastatic colorectal cancer (mCRC), but the emergence of resistance mutations restricts their efficacy. We previously showed that RAS, BRAF and EGFR mutant alleles, which appear in circulating tumor DNA (ctDNA) during EGFR blockade, decline upon therapy withdrawal. We hypothesized that monitoring resistance mutations in blood could rationally guide subsequent therapy with anti-EGFR antibodies. We report here the results of CHRONOS, an open-label, single-arm phase 2 clinical trial exploiting blood-based identification of RAS/BRAF/EGFR mutations levels to tailor a chemotherapy-free anti-EGFR rechallenge with panitumumab (ClinicalTrials.gov: NCT03227926 ; EudraCT 2016-002597-12). The primary endpoint was objective response rate. Secondary endpoints were progression-free survival, overall survival, safety and tolerability of this strategy. In CHRONOS, patients with tissue-RAS WT tumors after a previous treatment with anti-EGFR-based regimens underwent an interventional ctDNA-based screening. Of 52 patients, 16 (31%) carried at least one mutation conferring resistance to anti-EGFR therapy and were excluded. The primary endpoint of the trial was met; and, of 27 enrolled patients, eight (30%) achieved partial response and 17 (63%) disease control, including two unconfirmed responses. These clinical results favorably compare with standard third-line treatments and show that interventional liquid biopsies can be effectively and safely exploited in a timely manner to guide anti-EGFR rechallenge therapy with panitumumab in patients with mCRC. Further larger and randomized trials are warranted to formally compare panitumumab rechallenge with standard-of-care therapies in this patient setting.

Effect of dose splitting of a low-volume bowel preparation macrogol-based solution on CT colonography tagging quality.

PURPOSE: To compare examination quality and acceptability of three different low-volume bowel preparation regimens differing in scheduling of the oral administration of a Macrogol-based solution, in patients undergoing computed tomographic colonography (CTC). The secondary aim was to compare CTC quality according to anatomical and patient variables (dolichocolon, colonic diverticulosis, functional and secondary constipation). METHODS: One-hundred-eighty patients were randomized into one of three regimens where PEG was administered, respectively: in a single dose the day prior to (A), or in a fractionated dose 2 (B) and 3 days (C) before the examination. Two experienced radiologists evaluated fecal tagging (FT) density and homogeneity both qualitatively and quantitatively by assessing mean segment density (MSD) and relative standard deviation (RSD). Tolerance to the regimens and patient variables were also recorded. RESULTS: Compared to B and C, regimen A showed a lower percentage of segments with inadequate FT and a significantly higher median FT density and/or homogeneity scores as well as significantly higher MSD values in some colonic segments. No statistically significant differences were found in tolerance of the preparations. A higher number of inadequate segments were observed in patients with dolichocolon (p < 0.01) and secondary constipation (p < 0.01). Interobserver agreement was high for the assessment of both FT density (k = 0.887) and homogeneity (k = 0.852). CONCLUSION: The best examination quality was obtained when PEG was administered the day before CTC in a single session. The presence of dolichocolon and secondary constipation represent a risk factor for the presence of inadequately tagged colonic segments.

Integration of Deep Learning and Active Shape Models for More Accurate Prostate Segmentation in 3D MR Images.

Magnetic resonance imaging (MRI) has a growing role in the clinical workup of prostate cancer. However, manual three-dimensional (3D) segmentation of the prostate is a laborious and time-consuming task. In this scenario, the use of automated algorithms for prostate segmentation allows us to bypass the huge workload of physicians. In this work, we propose a fully automated hybrid approach for prostate gland segmentation in MR images using an initial segmentation of prostate volumes using a custom-made 3D deep network (VNet-T2), followed by refinement using an Active Shape Model (ASM). While the deep network focuses on three-dimensional spatial coherence of the shape, the ASM relies on local image information and this joint effort allows for improved segmentation of the organ contours. Our method is developed and tested on a dataset composed of T2-weighted (T2w) MRI prostatic volumes of 60 male patients. In the test set, the proposed method shows excellent segmentation performance, achieving a mean dice score and Hausdorff distance of 0.851 and 7.55 mm, respectively. In the future, this algorithm could serve as an enabling technology for the development of computer-aided systems for prostate cancer characterization in MR imaging.

MRI-based radiomics to predict response in locally advanced rectal cancer: comparison of manual and automatic segmentation on external validation in a multicentre study.

BACKGROUND: Pathological complete response after neoadjuvant chemoradiotherapy in locally advanced rectal cancer (LARC) is achieved in 15-30% of cases. Our aim was to implement and externally validate a magnetic resonance imaging (MRI)-based radiomics pipeline to predict response to treatment and to investigate the impact of manual and automatic segmentations on the radiomics models. METHODS: Ninety-five patients with stage II/III LARC who underwent multiparametric MRI before chemoradiotherapy and surgical treatment were enrolled from three institutions. Patients were classified as responders if tumour regression grade was 1 or 2 and nonresponders otherwise. Sixty-seven patients composed the construction dataset, while 28 the external validation. Tumour volumes were manually and automatically segmented using a U-net algorithm. Three approaches for feature selection were tested and combined with four machine learning classifiers. RESULTS: Using manual segmentation, the best result reached an accuracy of 68% on the validation set, with sensitivity 60%, specificity 77%, negative predictive value (NPV) 63%, and positive predictive value (PPV) 75%. The automatic segmentation achieved an accuracy of 75% on the validation set, with sensitivity 80%, specificity 69%, and both NPV and PPV 75%. Sensitivity and NPV on the validation set were significantly higher (p = 0.047) for the automatic versus manual segmentation. CONCLUSION: Our study showed that radiomics models can pave the way to help clinicians in the prediction of tumour response to chemoradiotherapy of LARC and to personalise per-patient treatment. The results from the external validation dataset are promising for further research into radiomics approaches using both manual and automatic segmentations.

Thoracic Spine CT Hidden Treasures: Lung Assessment and Extraspinal Findings in Patients with Vertebral Fractures Studied with Full FOV during Breath Hold: Technical Note.

Thoracic spine CTs are usually performed during free breathing and with a narrow field of view; this common practice systematically excludes the assessment of lungs and other extraspinal structures, even if these have been irradiated during the examination. At our institution we perform thoracic spine CT during breath hold with additional full FOV reconstructions; this allows us to also evaluate lungs and extraspinal pathologies in the same examination with no added costs or further radiation exposure. If this simple and costless technical change is routinely applied to thoracic spine CT many concomitant extraspinal pathologies can be ruled out, from neoplasms to pneumonia; the suggested modification also allows an early diagnosis and avoids recalling and re-irradiating the patient in case these findings are partially included in the study. This practice can be further useful during the current pandemic in order to screen any lung opacities suspicious for COVID-19.