Neural network algorithm for detection of erosions and ankylosis on CT of the sacroiliac joints: multicentre development and validation of diagnostic accuracy.

OBJECTIVES: To evaluate the feasibility and diagnostic accuracy of a deep learning network for detection of structural lesions of sacroiliitis on multicentre pelvic CT scans. METHODS: Pelvic CT scans of 145 patients (81 female, 121 Ghent University/24 Alberta University, 18-87 years old, mean 40 ± 13 years, 2005-2021) with a clinical suspicion of sacroiliitis were retrospectively included. After manual sacroiliac joint (SIJ) segmentation and structural lesion annotation, a U-Net for SIJ segmentation and two separate convolutional neural networks (CNN) for erosion and ankylosis detection were trained. In-training validation and tenfold validation testing (U-Net-n = 10 × 58; CNN-n = 10 × 29) on a test dataset were performed to assess performance on a slice-by-slice and patient level (dice coefficient/accuracy/sensitivity/specificity/positive and negative predictive value/ROC AUC). Patient-level optimisation was applied to increase the performance regarding predefined statistical metrics. Gradient-weighted class activation mapping (Grad-CAM++) heatmap explainability analysis highlighted image parts with statistically important regions for algorithmic decisions. RESULTS: Regarding SIJ segmentation, a dice coefficient of 0.75 was obtained in the test dataset. For slice-by-slice structural lesion detection, a sensitivity/specificity/ROC AUC of 95%/89%/0.92 and 93%/91%/0.91 were obtained in the test dataset for erosion and ankylosis detection, respectively. For patient-level lesion detection after pipeline optimisation for predefined statistical metrics, a sensitivity/specificity of 95%/85% and 82%/97% were obtained for erosion and ankylosis detection, respectively. Grad-CAM++ explainability analysis highlighted cortical edges as focus for pipeline decisions. CONCLUSIONS: An optimised deep learning pipeline, including an explainability analysis, detects structural lesions of sacroiliitis on pelvic CT scans with excellent statistical performance on a slice-by-slice and patient level. CLINICAL RELEVANCE STATEMENT: An optimised deep learning pipeline, including a robust explainability analysis, detects structural lesions of sacroiliitis on pelvic CT scans with excellent statistical metrics on a slice-by-slice and patient level. KEY POINTS: • Structural lesions of sacroiliitis can be detected automatically in pelvic CT scans. • Both automatic segmentation and disease detection yield excellent statistical outcome metrics. • The algorithm takes decisions based on cortical edges, rendering an explainable solution.

A Rare Case of Subcutaneous Amyloidoma Associated with Localized Lymphoplasmacytic Lymphoma: Diagnostic Challenges and Treatment Considerations.

BACKGROUND AL amyloidomas are solitary, localized, tumor-like deposits of immunoglobulin light-chain-derived amyloid fibrils in the absence of systemic amyloidosis. A rare entity, they have been described in various anatomical sites, typically in spatial association with a sparse lymphoplasmacytic infiltrate, ultimately corresponding to a clonal, malignant, lymphomatous disorder accounting for the amyloidogenic activity. Most frequently, the amyloidoma-associated hematological disorder corresponds to either a solitary plasmacytoma or an extranodal marginal zone lymphoma of MALT. Much rarer is the association with lymphoplasmacytic lymphoma, which by itself is usually a bone marrow-bound disorder with systemic burden. The almost anecdotic combination of an amyloidoma and a localized lymphoplasmacytic lymphoma deserves attention, as it entails a thorough diagnostic workup to exclude systemic involvement and a proportionate therapeutic approach to avoid overtreatment. A review of the literature provides an insight on pathogenesis and prognosis, and can assist both pathologists and clinicians in establishing optimal patient management strategies. CASE REPORT We herein report the incidental finding of a subcutaneous amyloidoma caused by a spatially related, similarly localized lymphoplasmacytic lymphoma diagnosed in a 54-year-old female patient with no other disease localizations and a complete remission following 2 subsequent surgical excisions. CONCLUSIONS Whatever the specific combination of an amyloidoma and the related hematological neoplasm, a multidisciplinary collaboration and a comprehensive clinical-pathological staging are warranted to exclude systemic involvement and identify patients with localized diseases who would benefit from local active treatment and close follow-up.

Disease Perception Is Correlated with Health-Related Quality of Life in Patients Suffering from Myelodysplastic Syndromes: Results of the Belgian Be-QUALMS Study.

Patients with myelodysplastic syndromes suffer from an impaired quality of life that is only partially explained by physical symptoms. In an observational study, we aimed to investigate the impact of current MDS treatments and the influence of disease perception on quality of life. Serial measurement of health-related quality of life was performed by 'the QUALMS', a validated MDS-specific patient reported outcome tool. Disease perception was evaluated by means of the Brief Illness Perception Questionnaire (B-IPQ). We prospectively collected data on 75 patients that started on a new treatment and could not demonstrate a significant change in QUALMS score or B-IPQ score during treatment. Six out of eight items evaluated in the B-IPQ correlated significantly with QUALMS score. In this small sample, no significant difference in QUALMS score was found between lower vs. higher risk MDS patients or other studied variables, e.g., targeted hemoglobin showed no correlation with QUALMS score. In daily practice attention must be paid to initial formation of disease perception as it correlates independently with health-related quality of life and does not change during treatment (clinicaltrials.gov identifier: NCT04053933).

Optimizing quality of life in multiple myeloma patients: current options, challenges and recommendations.

Multiple myeloma (MM) is a plasma cell neoplasm with a chronic disease course that primarily affects elderly individuals. The introduction of novel agents such as thalidomide, lenalidomide and bortezomib has significantly improved the outcome for MM patients, including the elderly. Quality of life in MM is influenced by disease-related symptoms, treatment-related toxicity and treatment response. In addition to conventional endpoints as response, quality of life should be carefully evaluated during each therapeutic phase. Caring for older adults with MM is particularly challenging because of the heterogeneity of aging and the presence of comorbidities and frailty, with a potential risk of over- or under-treatment. Moreover, elderly patients may sometimes prioritize maintaining quality of life above prolonging survival. A careful evaluation of comorbidities and a geriatric assessment can facilitate risk-stratification of elderly patients to identify the older population fit enough to tolerate standard drug dosing, and to detect the frail patients who need age-adapted treatment.