Multiple classification system for fracture detection in human bone x-ray images

Umadevi, N; Geethalakshmi, S. N.

doi:10.1109/icccnt.2012.6395889

Cited by 36 publications

(17 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The features selected can also be used to alleviate human labelling, by selecting more representative training data for the medical expert [ 81 , 82 ]. Another approach to the improvement of ML performance is the combination of several techniques using a majority vote scheme [ 75 ], or the use of multi-stage classifiers [ 58 ] for segmentation of different spatially related tissues.…”

Section: Discussionmentioning

confidence: 99%

“…X-rays have also been widely used for fracture detection, e.g. of the tibia [ 75 ], where texture and shape features were fed into three different ML algorithms: an ANN, k -NN, and SVM, and the outputs fused using a majority vote scheme. The combination of the classifiers using both types of features presented a significant improvement over using just one classifier, or only one feature type.…”

Section: Current Clinical Applicationsmentioning

confidence: 99%

See 1 more Smart Citation

Findings from machine learning in clinical medical imaging applications – Lessons for translation to the forensic setting

Peña-Solórzano

Albrecht

Bassed

et al. 2020

Forensic Science International

View full text Add to dashboard Cite

Highlights Machine learning techniques are currently not widely used in addressing forensic imaging problems. Machine learning applications can be transferred from clinical to forensic settings. Convolutional neural networks are outperforming other machine learning techniques in image processing tasks. There is a dearth of quantitative metrics presented for inter-study comparisons. A wider use of histopathological gold standard metrics for assessing algorithm performance is required.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Current Clinical Applicationsmentioning

confidence: 99%

Findings from machine learning in clinical medical imaging applications – Lessons for translation to the forensic setting

Peña-Solórzano

Albrecht

Bassed

et al. 2020

Forensic Science International

View full text Add to dashboard Cite

show abstract

“…Also, regions were not clearly demarcated according to those studies for different images of X-Ray. Some early studies also focused on identifying lung regions in chest X-Rays and they applied Markov Random field models [12], rule-based heuristics [13], and classifiers based on local features [14] with a different rate of success. One study has applied ASM for automatic segmentation of the patella in knee joint [15] with the help of a genetic algorithm.…”

Section: B Segmentation Of Bone From X-ray Images and Its Literaturementioning

confidence: 99%

An Audit of Computer Aided Fracture Detection System

Basha*,

Padmaja,

Balaji

2019

IJITEE

View full text Add to dashboard Cite

X-Ray images are the most widely recognized methods for medical imaging accessibility for individuals during the wounds and mishaps. X-rays are most frequent and the oldest form of medical imaging. Yet, the minute fracture identification using the X-Ray image is beyond the realm of imagination,because of the complication of bone organisation and the dissimilarity in visual attributes of fracture upon their location. This is the reason why it it is hard to detect the fractures and furthermore decide the seriousness of the damage. The major challenges of X-Ray imaging are the presence of noise, intensity ambiguity, and overlapping tissues. This creates a hurdle in correct diagnosis and delays treatment. The various rates require the human services experts to analyze countless x-ray images. computerized detection of fractures in X-Ray images can be a huge commitment for helping the doctors in settling on quicker and increasingly precise diagnostic decisions and speeds up the plan for the treatment. This research compares the existing fracture detection techniques.From various fractures, programmed identification is viewed as challenging since they are unique and variable in presentation and their results are quite un predictable.The major challenges for computer-aided fracture detection can be accurate segmentation process, automatic identification of the region of interest (bone fracture), evaluation and suggestive course of action.

show abstract

“…Sedangkan CT-scan sering digunakan pada kasus patah tulang yang kompleks yang memerlukan visualisasi tiga dimensi (3D) [6]. Kedua instrumen tersebut telah memberikan hasil yang sangat akurat dalam mendeteksi kondisi permukaan tulang dan deteksi terjadinya patah tulang [7]. Namun, kedua instrumen tersebut memiliki kelemahan dengan adanya efek negatif radiasi sinar X dan ionisasi yang tidak dianjurkan dipergunakan pada pasien anak kecil/bayi, wanita hamil, dan pada beberapa pasien khusus, yang dapat memicu timbulnya penyakit yang lain [7], [8].…”

unclassified

“…Kedua instrumen tersebut telah memberikan hasil yang sangat akurat dalam mendeteksi kondisi permukaan tulang dan deteksi terjadinya patah tulang [7]. Namun, kedua instrumen tersebut memiliki kelemahan dengan adanya efek negatif radiasi sinar X dan ionisasi yang tidak dianjurkan dipergunakan pada pasien anak kecil/bayi, wanita hamil, dan pada beberapa pasien khusus, yang dapat memicu timbulnya penyakit yang lain [7], [8]. Oleh karena itu, dibutuhkan adanya peralatan deteksi patah tulang yang aman tanpa efek radiasi untuk berbagai kategori pasien dan peralatan tersebut harus mudah dalam pengoperasian.…”

unclassified

Convolutional Neural Network untuk Pendeteksian Patah Tulang Femur pada Citra Ultrasonik B–Mode

Rokhana¹,

Priambodo²,

Karlita³

et al. 2019

Jurnal Nasional Teknik Elektro dan Teknologi Informasi

View full text Add to dashboard Cite

The bone fracture detection using X-rays or CTscan produces accurate images but has harmful effect radiation. This paper presented the use of ultrasonic waves (US) as an alternative to substitute those two instruments. This study used femur bovine and chicken bones in conditions with and without meat. The fractures are artificially made on transverse and oblique patterns. The scanning US probe produces twodimensional (2D) B-mode images. Fracture detection is done using five variations of the Convolutional Neural Network (CNN) architectural design, i.e., CNN1-CNN5. The results showed that the CNN4 is the best design of bone contour recognition and bone fracture classification compared to the other tested designs, with 95.3% accuracy, 95% sensitivity, and 96% specificity. The comparison with the Support Vector Machine (SVM) and k-NN classification methods indicate that CNN has superior performance in accuracy, sensitivity, and specificity. Intisari-Pendeteksian patah tulang dengan X-ray atau CTscan menghasilkan gambar yang akurat tetapi memiliki efek negatif radiasi yang berbahaya. Makalah ini memaparkan penggunaan gelombang ultrasonik (US) sebagai alternatif pengganti kedua instrumen tersebut. Makalah ini menggunakan tulang femur sapi dan ayam dalam kondisi dengan dan tanpa daging, dengan patahan dibuat secara manual dengan pola patah transverse dan oblique. Pemindaian probe US menghasilkan citra B-mode dua dimensi. Pendeteksian tulang patah dilakukan menggunakan lima variasi desain arsitektur Convolutional Neural Network (CNN), yaitu CNN1-CNN5. Hasil uji coba menunjukkan bahwa desain arsitektur CNN4 memberikan hasil pengenalan kontur tulang dan klasifikasi tulang patah yang paling bagus dibandingkan desain arsitektur lain yang diuji, dengan akurasi 95,3%, sensitivitas 95%, dan specificity 96%. Hasil perbandingan dengan metode klasifikasi Support Vector Machine (SVM) dan k-Neural Network (k-NN) menunjukkan bahwa CNN memiliki unjuk kerja yang lebih unggul baik dalam hal akurasi, sensitivitas, maupun specificity. Kata Kunci-Citra ultrasonik B-mode, Convolutional Neural Network, lapisan konvolusi, tulang femur.

show abstract

Multiple classification system for fracture detection in human bone x-ray images

Cited by 36 publications

References 29 publications

Findings from machine learning in clinical medical imaging applications – Lessons for translation to the forensic setting

Findings from machine learning in clinical medical imaging applications – Lessons for translation to the forensic setting

An Audit of Computer Aided Fracture Detection System

Convolutional Neural Network untuk Pendeteksian Patah Tulang Femur pada Citra Ultrasonik B–Mode

Contact Info

Product

Resources

About