Radiomics-based decision support tool assists radiologists in small lung nodule classification and improves lung cancer early diagnosis

BACKGROUND

Methods to improve stratification of small (≤15 mm) lung nodules are needed. We aimed to develop a radiomics model to assist lung cancer diagnosis.

METHODS

Patients were retrospectively identified using health records from January 2007 to December 2018. The external test set was obtained from the national LIBRA study and a prospective Lung Cancer Screening programme. Radiomics features were extracted from multi-region CT segmentations using TexLab2.0. LASSO regression generated the 5-feature small nodule radiomics-predictive-vector (SN-RPV). K-means clustering was used to split patients into risk groups according to SN-RPV. Model performance was compared to 6 thoracic radiologists. SN-RPV and radiologist risk groups were combined to generate "Safety-Net" and "Early Diagnosis" decision-support tools.

RESULTS

In total, 810 patients with 990 nodules were included. The AUC for malignancy prediction was 0.85 (95% CI: 0.82-0.87), 0.78 (95% CI: 0.70-0.85) and 0.78 (95% CI: 0.59-0.92) for the training, test and external test datasets, respectively. The test set accuracy was 73% (95% CI: 65-81%) and resulted in 66.67% improvements in potentially missed [8/12] or delayed [6/9] cancers, compared to the radiologist with performance closest to the mean of six readers.

CONCLUSIONS

SN-RPV may provide net-benefit in terms of earlier cancer diagnosis.

Tibial Retro-Malleolar Groove Morphology in Patients With Posterior Tibialis Tendon Dysfunction

The posterior tibial tendon is a gliding tendon which courses around the medial malleolus and fails in posterior tibialis tendon dysfunction (PTTD) leading to a flat foot deformity. Distal tibial bone spurs have been identified as a secondary sign of PTTD although they have not been quantified in detail. The aim of this study was to assess the association of tendon dysfunction with the bony morphology of the tibial retro-malleolar groove. We performed a retrospective review of the clinical presentation, plain radiographs, and 103 magnetic resonance imaging (MRI) scans in 82 consecutive patients with PTTD compared with a non-PTTD group. We carried out a quantitative and qualitative assessment of the presence of plain radiographic bone spurs, stage of PTTD and MRI imaging of the morphology of the tibial bony malleolar groove. Plain radiographic bone spurs, as a secondary sign of PTTD, were present in 21.3% of ankle radiographs. MRI bone spurs were identified in 26/41 (63.4%) for all high-grade partial and complete tears and 7/41 (17.1%) for isolated complete tears compared with only 3.9% of the non-PTTD group. There was a significant association between the presence of bone spurs on MRI imaging and high-grade partial and complete tibialis posterior tears (p < .001; odds ratio of 4.98). Eleven of 103 (10.7%) of spurs were large and in 4/103 (3.9%) were substantial enough to create a tunnel-like hypertrophic groove not previously reported. There is variation in the bony structure of the malleolar groove in PTTD not observed in the non-PTTD group. Further investigation over time may elucidate whether the groove morphology may lead to mechanical attrition of the tibialis posterior tendon and contribute to failure of healing and progressive tendon degeneration.

Differential diagnosis of hip pain in children referred to a specialist bone tumour service

OBJECTIVE

To determine the differential diagnosis of bone lesions causing hip pain in children and the association between radiographic features of aggression and MRI appearances with final diagnosis.

METHODS

Retrospective review of children with hip pain referred to a specialist musculoskeletal oncology service between September 2018 and December 2020. Patient demographics, lesion location, the radiographic and MRI features, and the final diagnosis, which was made either by image-guided biopsy, surgical curettage or based on typical imaging features were recorded. Statistical analysis examined the association between the Lodwick-Madewell score (determined from available radiographs) and MRI findings with final diagnosis.

RESULTS

Fifty-nine patients were included, 40 males and 19 females with mean age 10.9 years, (range 3-16 years). Final diagnoses were based on histology in 24 (40.7%) cases and imaging in 35 (59.3%) cases. Eighteen lesions (30.5%) were classed as non-neoplastic, 31 (52.5%) as benign and 10 (16.9%) as malignant, of which four were primary bone sarcomas. There was a significant association between the Lodwick-Madewell score and final diagnosis (p < 0.001). On MRI, bone marrow oedema, presence of a focal lesion, bone expansion and the presence of an extraosseous mass were all significantly associated with final diagnostic classification.

CONCLUSION

The differential diagnosis of hip pain in children presenting to a bone tumour service is wide. Most cases are due to benign or non-neoplastic conditions, with only 10 out of 59 children having a malignant lesion. Radiography complemented by MRI plays a major role in differentiating non-neoplastic, benign neoplastic and malignant lesions and in determining the requirement for needle biopsy.

ADVANCES IN KNOWLEDGE

This is the first study to consider how imaging features relate to diagnosis in suspected paediatric hip tumours. Use of this information can help in determining which cases should undergo needle biopsy.

Musculoskeletal imaging features of non-Langerhans cell histiocytoses

The non-Langerhans cell histiocytoses (N-LCH) represent a group of rare diseases with different clinical presentations and imaging features to classical LCH. While there is a long list of entities, only few present with musculoskeletal soft tissue and osseous manifestations alongside the more commonly reported systemic findings. Erdheim-Chester disease (ECD) is typically seen in adults as bilateral and symmetrical long bone osteosclerosis. Rosai-Dorfman disease (RDD) is more commonly seen in children and young adults with bone involvement usually being a manifestation of extra-nodal disease. Primary osseous RDD is very rare, with both displaying rather non-specific imaging features of an expansile lucent lesion with or without an extra-osseous component. Juvenile xanthogranuloma (JXG) is a benign disorder typically seen in very young children. The most common imaging manifestation is a dermal or sub-dermal soft tissue mass. This article reviews the musculoskeletal imaging appearances of the commoner N-LCH.

Radiological-pathological correlation of negative CT biopsy results enables high negative predictive value for thoracic malignancy

AIM

To evaluate multidisciplinary team (MDT) practice of radiological-pathological correlation of non-malignant biopsy results to examine the additive effect on the predictive values of computed tomography (CT) biopsy for malignancy and their subsequent management and outcomes.

MATERIALS AND METHODS

A service evaluation of the MDT management of non-malignant lung biopsy results (May 2014- May 2017) was undertaken.

RESULTS

Sixty patients had a non-malignant diagnosis on initial CT biopsy. Five patients were lost to follow-up leaving 55 in the final cohort. Forty-eight of the 55 patients had biopsy results classified as potentially non-specific, of which 26 were classified as concordant with radiology (e.g., organising pneumonia with compatible CT features), and 22 were classified as discordant (e.g., non-specific inflammation and yet sufficiently suspicious CT features). Patients with concordant negative pathology showed resolution (n=19) or stability (n=6) on imaging follow-up. One lesion demonstrated growth and was proven malignant on surgical resection. Discordant lesions were managed with repeat biopsy (n=8) or surgical resection (n=13), with 12 final benign diagnoses and nine malignancies. The negative predictive value of CT biopsy alone was 44/55 (80%), following repeat biopsy was 44/50 (88%), and following radiological-pathological assessment was 32/33 (97%). No patients underwent a shift in stage from time of biopsy to resection.

CONCLUSION

Combining radiological-pathological interpretation of negative biopsy results offers superior negative predictive value for lung malignancy without delayed diagnosis of lung cancer.

Distal radius fractures: an evidence-based approach to assessment and management

Distal radius fractures account for one in five bony injuries in both primary and secondary care. These are commonly the result of a fall on outstretched hands or high-energy trauma. On assessment, clinicians should determine the mechanism of injury, associated bony or soft tissue injuries, and neurovascular symptoms. Investigations should always include radiographs to evaluate for intra-articular involvement and fracture displacement. Owing to the heterogeneous injury patterns and patient profiles, the preferred management should consider the severity of the fracture, desired functional outcome and patient comorbidities. Non-operative management in select patients can give good results, especially in older adults. Immobilisation with or without reduction forms the mainstay of non-operative treatment. Surgical management options include closed reduction and application of a cast, percutaneous K-wires, open reduction and internal fixation with plates, or external fixation. Patients should be encouraged to mobilise as soon as it is safe to do so, to prevent stiffness. Median nerve compression is the most common complication followed by tendon rupture, arthrosis and malunion. This article outlines the British Orthopaedic Association Standards for Trauma and Orthopaedics for the management of distal radius fractures.

Sentinel and Non-Sentinel Lymph Node Metastasis Prediction and Validation of the MSKCC Nomograms for Indian Breast Cancer Patients

Background: Sentinel lymph node (SLN) biopsy accurately stages the axilla, but is time consuming and resource intensive. Nomograms and scoring systems have been developed, based on clinical and pathologic data available before surgery, to attempt to predict the likelihood of lymph node metastasis before surgery. As the management of the axilla in patients with low nodal burden changes, it is also important to predict whether there will be further axillary disease in patients with a positive SLN. Aim: To explore the risk factors for SLN and non-SLN metastasis in Indian women with breast cancer, by analysis of clinical and pathologic data. To assess the validity and clinical utility of two MSKCC nomograms that predicts axillary lymph node status for Western patients. Methods: Clinical data, and pathologic data available from core biopsy, for a consecutive series of women having SLNB was analyzed, and was plotted on two MSKCC nomograms. Univariate analysis was done by χ2 and Fischer exact tests and multivariate analysis was done by logistic regression method. A receiver-operating characteristic (ROC) curve was drawn and predictive accuracy was assessed by calculating the area under the ROC curve (AUC). Results: 34% (89 out of 256) of our patients had SLN positivity. When correlated with SLN metastasis by univariate analysis, LVI (χ2 = 80, P ≤ 0.001), PNI (χ2 = 13.36, P ≤ 0.001), ER+ (χ2 = 6.85, P = 0.009), PR+ (χ2 = 7.1, P = 0.008) and age ( P = 0.03) were significant. However, multivariate analysis showed that age (OR=1.04, P = 0.007) and LVI (OR=0.07, P ≤ 0.001) were identified as independent predictors for SLN metastasis. The area under the ROC curve was 0.772 and it fairly correlated with MSKCC nomogram. Patients with MSKCC scores lower than 38% had a frequency of SLN metastasis of 7.7% (5/65) and this cut-off could be used as a guide for not doing frozen section analysis in this subgroup. Further axillary dissection showed 41% (38 out of 92) had non-sentinel nodes positive. When correlated with non-SLN metastasis by univariate analysis, LVI (χ2 = 8.8, P = 0.003), PNI (χ2 = 6.85, P = 0.009), and extracapsular extension (χ2 = 4.18, P = 0.04) were significant. Number of SLN negative ( P = 0.01), SLN ratio (number of SLN positive/total number of SLN removed) ( P = 0.01) and size of SLN metastasis ( P = 0.002) were significant. However, multivariate analysis showed that only size of SLN metastasis (OR=0.845, P = 0.02) was identified as independent predictor for non-SLN metastasis. The area under the ROC curve was 0.66 and it poorly correlated with MSKCC nomogram. Conclusion: The MSKCC nomogram can provide a fairly accurate prediction of the probability of SLN metastasis, but is not for non-SLN metastasis. An institutional nomogram for non-SLN metastasis, including additional factors such as size of SLN metastasis, may improve prediction.