ARGO 2.0: a Hybrid NLP/ML Framework for Diagnosis Standardization.

A relevant problem in medicine is the standardization of the diagnosis associated with a clinical case. Although diagnosis formulation is an intrinsically subjective and uncertain process, its standardization may take benefit from digital solutions automating the routines at the basis of such a decision. In this work, we propose ARGO 2.0: a framework for the development of decision support systems for diagnosis formulation. The framework can read free-text reports and store their clinically relevant information as personalized electronic Case Report Forms. A hybrid strategy, exploiting the synergy of Natural Language Processing and Machine Learning techniques, is used to automatically suggest a diagnosis in a standardized fashion. ARGO 2.0 has been designed to be template-independent and easily tailored to specific medical fields. We here demonstrate its feasibility in hemo lympho-pathology, by detailing its implementation, object of an ongoing validation campaign in a standing medical institute. ARGO 2.0 achieved an average Accuracy of 95.07%, an average precision of 94.85%, an average Recall of 96.31% and a F-Score of 95.32% onto the test set, outperforming both its embedded components, based on Natural Language Processing and Machine Learning.

Performance and limitations of a supervised deep learning approach for the histopathological Oxford Classification of glomeruli with IgA nephropathy.

BACKGROUND AND OBJECTIVE: The Oxford Classification for IgA nephropathy is the most successful example of an evidence-based nephropathology classification system. The aim of our study was to replicate the glomerular components of Oxford scoring with an end-to-end deep learning pipeline that involves automatic glomerular segmentation followed by classification for mesangial hypercellularity (M), endocapillary hypercellularity (E), segmental sclerosis (S) and active crescents (C). METHODS: A total number of 1056 periodic acid-Schiff (PAS) whole slide images (WSIs), coming from 386 kidney biopsies, were annotated. Several detection models for glomeruli, based on the Mask R-CNN architecture, were trained on 587 WSIs, validated on 161 WSIs, and tested on 127 WSIs. For the development of segmentation models, 20,529 glomeruli were annotated, of which 16,571 as training and 3958 as validation set. The test set of the segmentation module comprised of 2948 glomeruli. For the Oxford classification, 6206 expert-annotated glomeruli from 308 PAS WSIs were labelled for M, E, S, C and split into a training set of 4298 glomeruli from 207 WSIs, and a test set of 1908 glomeruli. We chose the best-performing models to construct an end-to-end pipeline, which we named MESCnn (MESC classification by neural network), for the glomerular Oxford classification of WSIs. RESULTS: Instance segmentation yielded excellent results with an AP50 ranging between 78.2-80.1 % (79.4 ± 0.7 %) on the validation and 75.1-77.7 % (76.5 ± 0.9 %) on the test set. The aggregated Jaccard Index was between 73.4-75.9 % (75.0 ± 0.8 %) on the validation and 69.1-73.4 % (72.2 ± 1.4 %) on the test set. At granular glomerular level, Oxford Classification was best replicated for M with EfficientNetV2-L with a mean ROC-AUC of 90.2 % and a mean precision/recall area under the curve (PR-AUC) of 81.8 %, best for E with MobileNetV2 (ROC-AUC 94.7 %) and ResNet50 (PR-AUC 75.8 %), best for S with EfficientNetV2-M (mean ROC-AUC 92.7 %, mean PR-AUC 87.7 %), best for C with EfficientNetV2-L (ROC-AUC 92.3 %) and EfficientNetV2-S (PR-AUC 54.7 %). At biopsy-level, correlation between expert and deep learning labels fulfilled the demands of the Oxford Classification. CONCLUSION: We designed an end-to-end pipeline for glomerular Oxford Classification on both a granular glomerular and an entire biopsy level. Both the glomerular segmentation and the classification modules are freely available for further development to the renal medicine community.

Brain Linac-Based Radiation Therapy: "Test Drive" of New Immobilization Solution and Surface Guided Radiation Therapy.

AIM: To test inter-fraction reproducibility, intrafraction stability, technician aspects, and patient/physician's comfort of a dedicated immobilization solution for Brain Linac-based radiation therapy (RT). METHODS: A pitch-enabled head positioner with an open-face mask were used and, to evaluate inter- and intrafraction variations, 1-3 Cone-Beam Computed Tomography (CBCT) were performed. Surface Guided Radiation Therapy (SGRT) was used to evaluate intrafraction variations at 3 time points: initial (i), final (f), and monitoring (m) (before, end, and during RT). Data regarding technician mask aspect were collected. RESULTS: Between October 2019 and April 2020, 69 patients with brain disease were treated: 45 received stereotactic RT and 24 conventional RT; 556 treatment sessions and 863 CBCT's were performed. Inter-fraction CBCT mean values were longitudinally 0.9 mm, laterally 0.8 mm, vertically 1.1 mm, roll 0.58°, pitch 0.59°, yaw 0.67°. Intrafraction CBCT mean values were longitudinally 0.3 mm, laterally 0.3 mm, vertically 0.4 mm, roll 0.22°, pitch 0.33°, yaw 0.24°. SGRT intrafraction mean values were: i_, m_, f_ longitudinally 0.09 mm, 0.45 mm, 0.31 mm; i_, m_, f_ laterally 0.07 mm, 0.36 mm, 0.20 mm; i_, m_, f_ vertically 0.06 mm, 0.31 mm, 0.22 mm; i_, m_, f_ roll 0.025°, 0.208°, 0.118°; i_, m_, f_ pitch 0.036°, 0.307°, 0.194°; i_, m_, f_ yaw 0.039°, 0.274°, 0.189°. CONCLUSIONS: This immobilization solution is reproducible and stable. Combining CBCT and SGRT data confirm that 1 mm CTV-PTV margin for Linac-based SRT was adequate. Using open-face mask and SGRT, for conventional RT, radiological imaging could be omitted.