The ACROBAT 2022 challenge: Automatic registration of breast cancer tissue.

The alignment of tissue between histopathological whole-slide-images (WSI) is crucial for research and clinical applications. Advances in computing, deep learning, and availability of large WSI datasets have revolutionised WSI analysis. Therefore, the current state-of-the-art in WSI registration is unclear. To address this, we conducted the ACROBAT challenge, based on the largest WSI registration dataset to date, including 4,212 WSIs from 1,152 breast cancer patients. The challenge objective was to align WSIs of tissue that was stained with routine diagnostic immunohistochemistry to its H&E-stained counterpart. We compare the performance of eight WSI registration algorithms, including an investigation of the impact of different WSI properties and clinical covariates. We find that conceptually distinct WSI registration methods can lead to highly accurate registration performances and identify covariates that impact performances across methods. These results provide a comparison of the performance of current WSI registration methods and guide researchers in selecting and developing methods.

Deep learning-based risk stratification of preoperative breast biopsies using digital whole slide images.

BACKGROUND: Nottingham histological grade (NHG) is a well established prognostic factor in breast cancer histopathology but has a high inter-assessor variability with many tumours being classified as intermediate grade, NHG2. Here, we evaluate if DeepGrade, a previously developed model for risk stratification of resected tumour specimens, could be applied to risk-stratify tumour biopsy specimens. METHODS: A total of 11,955,755 tiles from 1169 whole slide images of preoperative biopsies from 896 patients diagnosed with breast cancer in Stockholm, Sweden, were included. DeepGrade, a deep convolutional neural network model, was applied for the prediction of low- and high-risk tumours. It was evaluated against clinically assigned grades NHG1 and NHG3 on the biopsy specimen but also against the grades assigned to the corresponding resection specimen using area under the operating curve (AUC). The prognostic value of the DeepGrade model in the biopsy setting was evaluated using time-to-event analysis. RESULTS: Based on preoperative biopsy images, the DeepGrade model predicted resected tumour cases of clinical grades NHG1 and NHG3 with an AUC of 0.908 (95% CI: 0.88; 0.93). Furthermore, out of the 432 resected clinically-assigned NHG2 tumours, 281 (65%) were classified as DeepGrade-low and 151 (35%) as DeepGrade-high. Using a multivariable Cox proportional hazards model the hazard ratio between DeepGrade low- and high-risk groups was estimated as 2.01 (95% CI: 1.06; 3.79). CONCLUSIONS: DeepGrade provided prediction of tumour grades NHG1 and NHG3 on the resection specimen using only the biopsy specimen. The results demonstrate that the DeepGrade model can provide decision support to identify high-risk tumours based on preoperative biopsies, thus improving early treatment decisions.

A Multi-Stain Breast Cancer Histological Whole-Slide-Image Data Set from Routine Diagnostics.

The analysis of FFPE tissue sections stained with haematoxylin and eosin (H&E) or immunohistochemistry (IHC) is essential for the pathologic assessment of surgically resected breast cancer specimens. IHC staining has been broadly adopted into diagnostic guidelines and routine workflows to assess the status of several established biomarkers, including ER, PGR, HER2 and KI67. Biomarker assessment can also be facilitated by computational pathology image analysis methods, which have made numerous substantial advances recently, often based on publicly available whole slide image (WSI) data sets. However, the field is still considerably limited by the sparsity of public data sets. In particular, there are no large, high quality publicly available data sets with WSIs of matching IHC and H&E-stained tissue sections from the same tumour. Here, we publish the currently largest publicly available data set of WSIs of tissue sections from surgical resection specimens from female primary breast cancer patients with matched WSIs of corresponding H&E and IHC-stained tissue, consisting of 4,212 WSIs from 1,153 patients.

Real-world clinical characterization, healthcare resource utilization and productivity loss in chronic graft versus host patients exposed to extracorporeal photopheresis in Sweden.

BACKGROUND: Extracorporeal photopheresis (ECP) is frequently used to treat moderate-severe chronic graft versus host disease (cGVHD), however limited data exists describing ECP treatment effects on healthcare and societal costs. We aimed to characterize clinical and health economic outcomes and productivity loss in cGVHD patients exposed to ECP. METHODS: We identified 2708 patients aged ≥ 18 years with a record of allogeneic hematopoietic stem cell transplantation (HSCT) in the Swedish Patient Register between 2006 and 2020. Patients exposed to ECP from 3-months post HSCT (index) were included (n= 183). Data was linked to the Prescribed Drug Register, the Cause of Death Register, and the Longitudinal Integrated Database for Health Insurance and Labor Market Studies (LISA). RESULTS: The median patient age at index was 51 years (IQR1-3; 38-61). In the 3-month period before ECP initiation compared to 9-12 months post-ECP, the cumulative three-month dose per patient decreased prednisolone/prednisone (1,381 mg vs. 658 mg, p < 0.001) and cyclosporin (12,242 mg vs. 3,501 mg, p < 0.001). Infection incidence also decreased over the same period (79.2% vs 59.1%, p < 0.001). Time spent in healthcare decreased from 68.9% to 22.1% from the first and fifth follow-up year respectively, and corresponding annual healthcare cost reduced from €27,719 to €1,981. Among patients < 66 years of age, sickness-related workplace absence decreased from 73.2% to 31.9% between the first and fifth follow-up year, with median annual productivity loss decreasing from €20,358 to €7,211 per patient. CONCLUSIONS: ECP was associated with reduced use of corticosteroids, immunosuppressive agents, and fewer infections. Furthermore, cost and healthcare utilization decreased over time.

Development and evaluation of deep learning algorithms for assessment of acute burns and the need for surgery.

Assessment of burn extent and depth are critical and require very specialized diagnosis. Automated image-based algorithms could assist in performing wound detection and classification. We aimed to develop two deep-learning algorithms that respectively identify burns, and classify whether they require surgery. An additional aim assessed the performances in different Fitzpatrick skin types. Annotated burn (n = 1105) and background (n = 536) images were collected. Using a commercially available platform for deep learning algorithms, two models were trained and validated on 70% of the images and tested on the remaining 30%. Accuracy was measured for each image using the percentage of wound area correctly identified and F1 scores for the wound identifier; and area under the receiver operating characteristic (AUC) curve, sensitivity, and specificity for the wound classifier. The wound identifier algorithm detected an average of 87.2% of the wound areas accurately in the test set. For the wound classifier algorithm, the AUC was 0.885. The wound identifier algorithm was more accurate in patients with darker skin types; the wound classifier was more accurate in patients with lighter skin types. To conclude, image-based algorithms can support the assessment of acute burns with relatively good accuracy although larger and different datasets are needed.

Adherence to Referral Criteria at Admission and Patient Management at a Specialized Burns Centre: The Case of the Red Cross War Memorial Children's Hospital in Cape Town, South Africa.

Referral guidelines for burn care are meant to assist in decision-making as regards patient transfer and admissions to specialized units. Little is known, however, concerning how closely they are followed and whether they are linked to patient care. This is the object of the current study, focused on the paediatric burns centre of the Red Cross War Memorial Children's Hospital in Cape Town, South Africa. All patients admitted to the centre during the winters of 2011-2015 (n = 1165) were included. The patient files were scrutinized to clarify whether the referral criteria in place were identified (seven in total) and to compile data on patient and injury characteristics. A case was defined as adherent to the criteria when at least one criterion was fulfilled and adherence was expressed as a percentage with 95% confidence intervals, for all years aggregated as well as by year and by patient or injury characteristics. The association between adherence to any individual criterion and hospital care (surgery or longer length of stay) was measured using logistic regressions. The overall adherence was 93.4% (100% among children under 2 years of age and 86% among the others) and it did not vary remarkably over time. The two criteria of "injury sustained at a specific anatomical site" (85.2%) and "young age" (51.9%) were those most often identified. Children aged 2 years or older were more likely to undergo surgery or to stay longer than those of young age (although a referral criterion) and so were those with higher injury severity (a referral criterion). In this specialized paediatric burns centre, children are admitted mainly according to the guidelines. However, given the high prevalence of paediatric burns in the region and the limited resources at the burns centre, adherence to the guidelines need to be further studied at all healthcare levels in the province.